[{"month":"12","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","status":"public","publisher":"Cell Press","title":"Hydroxyurea triggers cellular responses that actively cause bacterial cell death","author":[{"full_name":"Bollenbach, Mark Tobias","orcid":"0000-0003-4398-476X","first_name":"Mark Tobias","id":"3E6DB97A-F248-11E8-B48F-1D18A9856A87","last_name":"Bollenbach"},{"first_name":"Roy","last_name":"Kishony","full_name":"Kishony, Roy"}],"_id":"3428","abstract":[{"lang":"eng","text":"In this issue of Molecular Cell, Davies et al. (2009) work out a sequence of active cellular events that lead to the death of Escherichia coli in the presence of the drug hydroxyurea."}],"issue":"5","date_updated":"2021-01-12T07:43:24Z","extern":"1","year":"2009","day":"11","citation":{"ama":"Bollenbach MT, Kishony R. Hydroxyurea triggers cellular responses that actively cause bacterial cell death. <i>Molecular Cell</i>. 2009;36(5):728-729. doi:<a href=\"https://doi.org/10.1016/j.molcel.2009.11.027\">10.1016/j.molcel.2009.11.027</a>","ieee":"M. T. Bollenbach and R. Kishony, “Hydroxyurea triggers cellular responses that actively cause bacterial cell death,” <i>Molecular Cell</i>, vol. 36, no. 5. Cell Press, pp. 728–729, 2009.","short":"M.T. Bollenbach, R. Kishony, Molecular Cell 36 (2009) 728–729.","chicago":"Bollenbach, Mark Tobias, and Roy Kishony. “Hydroxyurea Triggers Cellular Responses That Actively Cause Bacterial Cell Death.” <i>Molecular Cell</i>. Cell Press, 2009. <a href=\"https://doi.org/10.1016/j.molcel.2009.11.027\">https://doi.org/10.1016/j.molcel.2009.11.027</a>.","apa":"Bollenbach, M. T., &#38; Kishony, R. (2009). Hydroxyurea triggers cellular responses that actively cause bacterial cell death. <i>Molecular Cell</i>. Cell Press. <a href=\"https://doi.org/10.1016/j.molcel.2009.11.027\">https://doi.org/10.1016/j.molcel.2009.11.027</a>","ista":"Bollenbach MT, Kishony R. 2009. Hydroxyurea triggers cellular responses that actively cause bacterial cell death. Molecular Cell. 36(5), 728–729.","mla":"Bollenbach, Mark Tobias, and Roy Kishony. “Hydroxyurea Triggers Cellular Responses That Actively Cause Bacterial Cell Death.” <i>Molecular Cell</i>, vol. 36, no. 5, Cell Press, 2009, pp. 728–29, doi:<a href=\"https://doi.org/10.1016/j.molcel.2009.11.027\">10.1016/j.molcel.2009.11.027</a>."},"intvolume":"        36","volume":36,"article_processing_charge":"No","publist_id":"2972","oa_version":"None","type":"journal_article","date_published":"2009-12-11T00:00:00Z","language":[{"iso":"eng"}],"doi":"10.1016/j.molcel.2009.11.027","publication_status":"published","publication":"Molecular Cell","page":"728 - 729","date_created":"2018-12-11T12:03:17Z"},{"status":"public","publisher":"Springer","title":"Probabilistic systems with limsup and liminf objectives","oa":1,"month":"12","alternative_title":["LNCS"],"date_updated":"2021-01-12T07:43:54Z","abstract":[{"lang":"eng","text":"We give polynomial-time algorithms for computing the values of Markov decision processes (MDPs) with limsup and liminf objectives. A real-valued reward is assigned to each state, and the value of an infinite path in the MDP is the limsup (resp. liminf) of all rewards along the path. The value of an MDP is the maximal expected value of an infinite path that can be achieved by resolving the decisions of the MDP. Using our result on MDPs, we show that turn-based stochastic games with limsup and liminf objectives can be solved in NP ∩ coNP. "}],"day":"15","year":"2009","extern":1,"author":[{"id":"2E5DCA20-F248-11E8-B48F-1D18A9856A87","last_name":"Chatterjee","orcid":"0000-0002-4561-241X","first_name":"Krishnendu","full_name":"Krishnendu Chatterjee"},{"full_name":"Thomas Henzinger","first_name":"Thomas A","orcid":"0000−0002−2985−7724","id":"40876CD8-F248-11E8-B48F-1D18A9856A87","last_name":"Henzinger"}],"_id":"3503","publist_id":"2884","main_file_link":[{"url":"http://arxiv.org/abs/0809.1465","open_access":"1"}],"intvolume":"      5489","quality_controlled":0,"citation":{"apa":"Chatterjee, K., &#38; Henzinger, T. A. (2009). Probabilistic systems with limsup and liminf objectives (Vol. 5489, pp. 32–45). Presented at the ILC: Infinity in Logic and Computation, Springer. <a href=\"https://doi.org/10.1007/978-3-642-03092-5_4\">https://doi.org/10.1007/978-3-642-03092-5_4</a>","ista":"Chatterjee K, Henzinger TA. 2009. Probabilistic systems with limsup and liminf objectives. ILC: Infinity in Logic and Computation, LNCS, vol. 5489, 32–45.","mla":"Chatterjee, Krishnendu, and Thomas A. Henzinger. <i>Probabilistic Systems with Limsup and Liminf Objectives</i>. Vol. 5489, Springer, 2009, pp. 32–45, doi:<a href=\"https://doi.org/10.1007/978-3-642-03092-5_4\">10.1007/978-3-642-03092-5_4</a>.","chicago":"Chatterjee, Krishnendu, and Thomas A Henzinger. “Probabilistic Systems with Limsup and Liminf Objectives,” 5489:32–45. Springer, 2009. <a href=\"https://doi.org/10.1007/978-3-642-03092-5_4\">https://doi.org/10.1007/978-3-642-03092-5_4</a>.","short":"K. Chatterjee, T.A. Henzinger, in:, Springer, 2009, pp. 32–45.","ieee":"K. Chatterjee and T. A. Henzinger, “Probabilistic systems with limsup and liminf objectives,” presented at the ILC: Infinity in Logic and Computation, 2009, vol. 5489, pp. 32–45.","ama":"Chatterjee K, Henzinger TA. Probabilistic systems with limsup and liminf objectives. In: Vol 5489. Springer; 2009:32-45. doi:<a href=\"https://doi.org/10.1007/978-3-642-03092-5_4\">10.1007/978-3-642-03092-5_4</a>"},"volume":5489,"publication_status":"published","conference":{"name":"ILC: Infinity in Logic and Computation"},"doi":"10.1007/978-3-642-03092-5_4","date_created":"2018-12-11T12:03:40Z","page":"32 - 45","type":"conference","date_published":"2009-12-15T00:00:00Z"},{"volume":61,"quality_controlled":0,"intvolume":"        61","citation":{"chicago":"Remy, Stefan, Jozsef L Csicsvari, and Heinz Beck. “Activity-Dependent Control of Neuronal Output by Local and Global Dendritic Spike Attenuation.” <i>Neuron</i>. Elsevier, 2009. <a href=\"https://doi.org/10.1016/j.neuron.2009.01.032\">https://doi.org/10.1016/j.neuron.2009.01.032</a>.","apa":"Remy, S., Csicsvari, J. L., &#38; Beck, H. (2009). Activity-dependent control of neuronal output by local and global dendritic spike attenuation. <i>Neuron</i>. Elsevier. <a href=\"https://doi.org/10.1016/j.neuron.2009.01.032\">https://doi.org/10.1016/j.neuron.2009.01.032</a>","mla":"Remy, Stefan, et al. “Activity-Dependent Control of Neuronal Output by Local and Global Dendritic Spike Attenuation.” <i>Neuron</i>, vol. 61, no. 6, Elsevier, 2009, pp. 906–16, doi:<a href=\"https://doi.org/10.1016/j.neuron.2009.01.032\">10.1016/j.neuron.2009.01.032</a>.","ista":"Remy S, Csicsvari JL, Beck H. 2009. Activity-dependent control of neuronal output by local and global dendritic spike attenuation. Neuron. 61(6), 906–916.","ieee":"S. Remy, J. L. Csicsvari, and H. Beck, “Activity-dependent control of neuronal output by local and global dendritic spike attenuation,” <i>Neuron</i>, vol. 61, no. 6. Elsevier, pp. 906–916, 2009.","ama":"Remy S, Csicsvari JL, Beck H. Activity-dependent control of neuronal output by local and global dendritic spike attenuation. <i>Neuron</i>. 2009;61(6):906-916. doi:<a href=\"https://doi.org/10.1016/j.neuron.2009.01.032\">10.1016/j.neuron.2009.01.032</a>","short":"S. Remy, J.L. Csicsvari, H. Beck, Neuron 61 (2009) 906–916."},"publist_id":"2838","date_published":"2009-03-26T00:00:00Z","type":"journal_article","page":"906 - 916","date_created":"2018-12-11T12:03:54Z","publication":"Neuron","publication_status":"published","doi":"10.1016/j.neuron.2009.01.032","month":"03","title":"Activity-dependent control of neuronal output by local and global dendritic spike attenuation","status":"public","publisher":"Elsevier","_id":"3547","author":[{"first_name":"Stefan","last_name":"Remy","full_name":"Remy,Stefan"},{"full_name":"Jozsef Csicsvari","orcid":"0000-0002-5193-4036","first_name":"Jozsef L","last_name":"Csicsvari","id":"3FA14672-F248-11E8-B48F-1D18A9856A87"},{"full_name":"Beck,Heinz","first_name":"Heinz","last_name":"Beck"}],"day":"26","year":"2009","extern":1,"date_updated":"2021-01-12T07:44:13Z","issue":"6","abstract":[{"lang":"eng","text":"Neurons possess elaborate dendritic arbors which receive and integrate excitatory synaptic signals. Individual dendritic subbranches exhibit local membrane potential supralinearities, termed dendritic spikes, which control transfer of local synaptic input to the soma. Here, we show that dendritic spikes in CA1 pyramidal cells are strongly regulated by specific types of prior input. While input in the linear range is without effect, supralinear input inhibits subsequent spikes, causing them to attenuate and ultimately fail due to dendritic Na+ channel inactivation. This mechanism acts locally within the boundaries of the input branch. If an input is sufficiently strong to trigger axonal action potentials, their back-propagation into the dendritic tree causes a widespread global reduction in dendritic excitability which is prominent after firing patterns occurring in vivo. Together, these mechanisms control the capability of individual dendritic branches to trigger somatic action potential output. They are invoked at frequencies encountered during learning, and impose limits on the storage and retrieval rates of information encoded as branch excitability."}]},{"author":[{"full_name":"Attali, Dominique","last_name":"Attali","first_name":"Dominique"},{"first_name":"Jean","last_name":"Boissonnat","full_name":"Boissonnat, Jean-Daniel"},{"full_name":"Herbert Edelsbrunner","orcid":"0000-0002-9823-6833","first_name":"Herbert","last_name":"Edelsbrunner","id":"3FB178DA-F248-11E8-B48F-1D18A9856A87"}],"_id":"3578","abstract":[{"text":"The medial axis of a geometric shape captures its connectivity. In spite of its inherent instability, it has found applications in a number of areas that deal with shapes. In this survey paper, we focus on results that shed light on this instability and use the new insights to generate simplified and stable modifications of the medial axis.","lang":"eng"}],"date_updated":"2021-01-12T07:44:25Z","extern":1,"year":"2009","day":"22","alternative_title":["Mathematics and Visualization"],"month":"06","publisher":"Springer","status":"public","title":"Stability and computation of medial axes: a state-of-the-art report","type":"book_chapter","date_published":"2009-06-22T00:00:00Z","doi":"10.1007/b106657_6","publication_status":"published","publication":"Mathematical Foundations of Scientific Visualization, Computer Graphics, and Massive Data Exploration","date_created":"2018-12-11T12:04:03Z","page":"109 - 125","quality_controlled":0,"citation":{"chicago":"Attali, Dominique, Jean Boissonnat, and Herbert Edelsbrunner. “Stability and Computation of Medial Axes: A State-of-the-Art Report.” In <i>Mathematical Foundations of Scientific Visualization, Computer Graphics, and Massive Data Exploration</i>, 109–25. Springer, 2009. <a href=\"https://doi.org/10.1007/b106657_6\">https://doi.org/10.1007/b106657_6</a>.","apa":"Attali, D., Boissonnat, J., &#38; Edelsbrunner, H. (2009). Stability and computation of medial axes: a state-of-the-art report. In <i>Mathematical Foundations of Scientific Visualization, Computer Graphics, and Massive Data Exploration</i> (pp. 109–125). Springer. <a href=\"https://doi.org/10.1007/b106657_6\">https://doi.org/10.1007/b106657_6</a>","ista":"Attali D, Boissonnat J, Edelsbrunner H. 2009.Stability and computation of medial axes: a state-of-the-art report. In: Mathematical Foundations of Scientific Visualization, Computer Graphics, and Massive Data Exploration. Mathematics and Visualization, , 109–125.","mla":"Attali, Dominique, et al. “Stability and Computation of Medial Axes: A State-of-the-Art Report.” <i>Mathematical Foundations of Scientific Visualization, Computer Graphics, and Massive Data Exploration</i>, Springer, 2009, pp. 109–25, doi:<a href=\"https://doi.org/10.1007/b106657_6\">10.1007/b106657_6</a>.","ama":"Attali D, Boissonnat J, Edelsbrunner H. Stability and computation of medial axes: a state-of-the-art report. In: <i>Mathematical Foundations of Scientific Visualization, Computer Graphics, and Massive Data Exploration</i>. Springer; 2009:109-125. doi:<a href=\"https://doi.org/10.1007/b106657_6\">10.1007/b106657_6</a>","ieee":"D. Attali, J. Boissonnat, and H. Edelsbrunner, “Stability and computation of medial axes: a state-of-the-art report,” in <i>Mathematical Foundations of Scientific Visualization, Computer Graphics, and Massive Data Exploration</i>, Springer, 2009, pp. 109–125.","short":"D. Attali, J. Boissonnat, H. Edelsbrunner, in:, Mathematical Foundations of Scientific Visualization, Computer Graphics, and Massive Data Exploration, Springer, 2009, pp. 109–125."},"publist_id":"2807","main_file_link":[{"open_access":"0","url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.103.9122"}]},{"intvolume":"        74","quality_controlled":"1","citation":{"ieee":"N. H. Barton, “Why sex and recombination? ,” in <i>Cold Spring Harbor Symposia on Quantitative Biology</i>, vol. 74, Cold Spring Harbor Laboratory Press, 2009, pp. 187–195.","ama":"Barton NH. Why sex and recombination? . In: <i>Cold Spring Harbor Symposia on Quantitative Biology</i>. Vol 74. Cold Spring Harbor Laboratory Press; 2009:187-195. doi:<a href=\"https://doi.org/10.1101/sqb.2009.74.030\">10.1101/sqb.2009.74.030</a>","short":"N.H. Barton, in:, Cold Spring Harbor Symposia on Quantitative Biology, Cold Spring Harbor Laboratory Press, 2009, pp. 187–195.","chicago":"Barton, Nicholas H. “Why Sex and Recombination? .” In <i>Cold Spring Harbor Symposia on Quantitative Biology</i>, 74:187–95. Cold Spring Harbor Laboratory Press, 2009. <a href=\"https://doi.org/10.1101/sqb.2009.74.030\">https://doi.org/10.1101/sqb.2009.74.030</a>.","ista":"Barton NH. 2009.Why sex and recombination? . In: Cold Spring Harbor Symposia on Quantitative Biology. vol. 74, 187–195.","mla":"Barton, Nicholas H. “Why Sex and Recombination? .” <i>Cold Spring Harbor Symposia on Quantitative Biology</i>, vol. 74, Cold Spring Harbor Laboratory Press, 2009, pp. 187–95, doi:<a href=\"https://doi.org/10.1101/sqb.2009.74.030\">10.1101/sqb.2009.74.030</a>.","apa":"Barton, N. H. (2009). Why sex and recombination? . In <i>Cold Spring Harbor Symposia on Quantitative Biology</i> (Vol. 74, pp. 187–195). Cold Spring Harbor Laboratory Press. <a href=\"https://doi.org/10.1101/sqb.2009.74.030\">https://doi.org/10.1101/sqb.2009.74.030</a>"},"volume":74,"scopus_import":1,"publist_id":"2708","department":[{"_id":"NiBa"}],"date_published":"2009-11-10T00:00:00Z","language":[{"iso":"eng"}],"oa_version":"None","type":"book_chapter","publication":"Cold Spring Harbor Symposia on Quantitative Biology","date_created":"2018-12-11T12:04:33Z","page":"187 - 195","doi":"10.1101/sqb.2009.74.030","publication_status":"published","month":"11","title":"Why sex and recombination? ","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","status":"public","publisher":"Cold Spring Harbor Laboratory Press","_id":"3675","author":[{"full_name":"Barton, Nicholas H","orcid":"0000-0002-8548-5240","first_name":"Nicholas H","last_name":"Barton","id":"4880FE40-F248-11E8-B48F-1D18A9856A87"}],"year":"2009","day":"10","abstract":[{"lang":"eng","text":"Sex and recombination have long been seen as adaptations that facilitate natural selection by generating favorable variations. If recombination is to aid selection, there must be negative linkage disequilibria—favorable alleles must be found together less often than expected by chance. These negative linkage disequilibria can be generated directly by selection, but this must involve negative epistasis of just the right strength, which is not expected, from either experiment or theory. Random drift provides a more general source of negative associations: Favorable mutations almost always arise on different genomes, and negative associations tend to persist, precisely because they shield variation from selection.\r\n\r\nWe can understand how recombination aids adaptation by determining the maximum possible rate of adaptation. With unlinked loci, this rate increases only logarithmically with the influx of favorable mutations. With a linear genome, a scaling argument shows that in a large population, the rate of adaptive substitution depends only on the expected rate in the absence of interference, divided by the total rate of recombination. A two-locus approximation predicts an upper bound on the rate of substitution, proportional to recombination rate.\r\n\r\nIf associations between linked loci do impede adaptation, there can be substantial selection for modifiers that increase recombination. Whether this can account for the maintenance of high rates of sex and recombination depends on the extent of selection. It is clear that the rate of species-wide substitutions is typically far too low to generate appreciable selection for recombination. However, local sweeps within a subdivided population may be effective."}],"acknowledgement":"Royal Society and the Engineering and Physical Sciences for support (GR/ T11753/01)","date_updated":"2021-01-12T07:45:04Z"},{"conference":{"name":"CVPR: Computer Vision and Pattern Recognition"},"publication_status":"published","doi":"10.1109/CVPRW.2009.5204237","page":"22 - 29","date_created":"2018-12-11T12:04:38Z","type":"conference","date_published":"2009-01-01T00:00:00Z","publist_id":"2675","citation":{"ieee":"P. Dhillon, S. Nowozin, and C. Lampert, “Combining appearance and motion for human action classification in videos,” presented at the CVPR: Computer Vision and Pattern Recognition, 2009, no. 174, pp. 22–29.","ama":"Dhillon P, Nowozin S, Lampert C. Combining appearance and motion for human action classification in videos. In: IEEE; 2009:22-29. doi:<a href=\"https://doi.org/10.1109/CVPRW.2009.5204237\">10.1109/CVPRW.2009.5204237</a>","short":"P. Dhillon, S. Nowozin, C. Lampert, in:, IEEE, 2009, pp. 22–29.","mla":"Dhillon, Paramveer, et al. <i>Combining Appearance and Motion for Human Action Classification in Videos</i>. no. 174, IEEE, 2009, pp. 22–29, doi:<a href=\"https://doi.org/10.1109/CVPRW.2009.5204237\">10.1109/CVPRW.2009.5204237</a>.","ista":"Dhillon P, Nowozin S, Lampert C. 2009. Combining appearance and motion for human action classification in videos. CVPR: Computer Vision and Pattern Recognition, 22–29.","apa":"Dhillon, P., Nowozin, S., &#38; Lampert, C. (2009). Combining appearance and motion for human action classification in videos (pp. 22–29). Presented at the CVPR: Computer Vision and Pattern Recognition, IEEE. <a href=\"https://doi.org/10.1109/CVPRW.2009.5204237\">https://doi.org/10.1109/CVPRW.2009.5204237</a>","chicago":"Dhillon, Paramveer, Sebastian Nowozin, and Christoph Lampert. “Combining Appearance and Motion for Human Action Classification in Videos,” 22–29. IEEE, 2009. <a href=\"https://doi.org/10.1109/CVPRW.2009.5204237\">https://doi.org/10.1109/CVPRW.2009.5204237</a>."},"quality_controlled":0,"date_updated":"2021-01-12T07:48:59Z","abstract":[{"text":"An important cue to high level scene understanding is to analyze the objects in the scene and their behavior and interactions. In this paper, we study the problem of classification of activities in videos, as this is an integral component of any scene understanding system, and present a novel approach for recognizing human action categories in videos by combining information from appearance and motion of human body parts. Our approach is based on tracking human body parts by using mixture particle filters and then clustering the particles using local non - parametric clustering, hence associating a local set of particles to each cluster mode. The trajectory of these cluster modes provides the &quot;motion&quot; information and the &quot;appearance&quot; information is provided by the statistical information about the relative motion of these local set of particles over a number of frames. Later we use a &quot;Bag of Words&quot; model to build one histogram per video sequence from the set of these robust appearance and motion descriptors. These histograms provide us characteristic information which helps us to discriminate among various human actions which ultimately helps us in better understanding of the complete scene. We tested our approach on the standard KTH and Weizmann human action dataseis and the results were comparable to the state of the art methods. Additionally our approach is able to distinguish between activities that involve the motion of complete body from those in which only certain body parts move. In other words, our method discriminates well between activities with &quot;global body motion&quot; like running, jogging etc. and &quot;local motion&quot; like waving, boxing etc.","lang":"eng"}],"issue":"174","day":"01","extern":1,"year":"2009","author":[{"full_name":"Dhillon, Paramveer S","first_name":"Paramveer","last_name":"Dhillon"},{"full_name":"Nowozin, Sebastian","first_name":"Sebastian","last_name":"Nowozin"},{"full_name":"Christoph Lampert","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","last_name":"Lampert","orcid":"0000-0001-8622-7887","first_name":"Christoph"}],"_id":"3690","publisher":"IEEE","status":"public","title":"Combining appearance and motion for human action classification in videos","month":"01"},{"publication_status":"published","doi":"10.1007/s10994-009-5111-0","date_created":"2018-12-11T12:04:40Z","page":"249 - 269","publication":"Machine Learning","type":"journal_article","date_published":"2009-04-07T00:00:00Z","publist_id":"2663","volume":77,"citation":{"chicago":"Lampert, Christoph, and Matthew Blaschko. “Structured Prediction by Joint Kernel Support Estimation.” <i>Machine Learning</i>. Springer, 2009. <a href=\"https://doi.org/10.1007/s10994-009-5111-0\">https://doi.org/10.1007/s10994-009-5111-0</a>.","mla":"Lampert, Christoph, and Matthew Blaschko. “Structured Prediction by Joint Kernel Support Estimation.” <i>Machine Learning</i>, vol. 77, no. 2–3, Springer, 2009, pp. 249–69, doi:<a href=\"https://doi.org/10.1007/s10994-009-5111-0\">10.1007/s10994-009-5111-0</a>.","apa":"Lampert, C., &#38; Blaschko, M. (2009). Structured prediction by joint kernel support estimation. <i>Machine Learning</i>. Springer. <a href=\"https://doi.org/10.1007/s10994-009-5111-0\">https://doi.org/10.1007/s10994-009-5111-0</a>","ista":"Lampert C, Blaschko M. 2009. Structured prediction by joint kernel support estimation. Machine Learning. 77(2–3), 249–269.","ieee":"C. Lampert and M. Blaschko, “Structured prediction by joint kernel support estimation,” <i>Machine Learning</i>, vol. 77, no. 2–3. Springer, pp. 249–269, 2009.","ama":"Lampert C, Blaschko M. Structured prediction by joint kernel support estimation. <i>Machine Learning</i>. 2009;77(2-3):249-269. doi:<a href=\"https://doi.org/10.1007/s10994-009-5111-0\">10.1007/s10994-009-5111-0</a>","short":"C. Lampert, M. Blaschko, Machine Learning 77 (2009) 249–269."},"intvolume":"        77","quality_controlled":0,"date_updated":"2021-01-12T07:49:01Z","issue":"2-3","abstract":[{"lang":"eng","text":"Discriminative techniques, such as conditional random fields (CRFs) or structure aware maximum-margin techniques (maximum margin Markov networks (M3N), structured output support vector machines (S-SVM)), are state-of-the-art in the prediction of structured data. However, to achieve good results these techniques require complete and reliable ground truth, which is not always available in realistic problems. Furthermore, training either CRFs or margin-based techniques is computationally costly, because the runtime of current training methods depends not only on the size of the training set but also on properties of the output space to which the training samples are assigned. We propose an alternative model for structured output prediction, Joint Kernel Support Estimation (JKSE), which is rather generative in nature as it relies on estimating the joint probability density of samples and labels in the training set. This makes it tolerant against incomplete or incorrect labels and also opens the possibility of learning in situations where more than one output label can be considered correct. At the same time, we avoid typical problems of generative models as we do not attempt to learn the full joint probability distribution, but we model only its support in a joint reproducing kernel Hilbert space. As a consequence, JKSE training is possible by an adaption of the classical one-class SVM procedure. The resulting optimization problem is convex and efficiently solvable even with tens of thousands of training examples. A particular advantage of JKSE is that the training speed depends only on the size of the training set, and not on the total size of the label space. No inference step during training is required (as M3N and S-SVM would) nor do we have calculate a partition function (as CRFs do). Experiments on realistic data show that, for suitable kernel functions, our method works efficiently and robustly in situations that discriminative techniques have problems with or that are computationally infeasible for them."}],"tmp":{"image":"/images/cc_by_nc.png","short":"CC BY-NC (4.0)","legal_code_url":"https://creativecommons.org/licenses/by-nc/4.0/legalcode","name":"Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)"},"day":"07","year":"2009","extern":1,"author":[{"full_name":"Christoph Lampert","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","last_name":"Lampert","first_name":"Christoph","orcid":"0000-0001-8622-7887"},{"last_name":"Blaschko","first_name":"Matthew","full_name":"Blaschko,Matthew B"}],"_id":"3696","publisher":"Springer","status":"public","title":"Structured prediction by joint kernel support estimation","month":"04"},{"main_file_link":[{"open_access":"0","url":"http://pubman.mpdl.mpg.de/pubman/faces/viewItemOverviewPage.jsp?itemId=escidoc:1789281"}],"publist_id":"2661","quality_controlled":0,"citation":{"ama":"Blaschko M, Lampert C, Bartels A. <i>Semi-Supervised Analysis of Human FMRI Data</i>. Berlin Institute of Technology; 2009.","ieee":"M. Blaschko, C. Lampert, and A. Bartels, <i>Semi-supervised analysis of human fMRI data</i>. Berlin Institute of Technology, 2009.","short":"M. Blaschko, C. Lampert, A. Bartels, Semi-Supervised Analysis of Human FMRI Data, Berlin Institute of Technology, 2009.","apa":"Blaschko, M., Lampert, C., &#38; Bartels, A. (2009). <i>Semi-supervised analysis of human fMRI data</i>. <i>BBCI: Berlin Brain-Computer Interface Workshop - Advances in Neurotechnology</i>. Berlin Institute of Technology.","ista":"Blaschko M, Lampert C, Bartels A. 2009. Semi-supervised analysis of human fMRI data, Berlin Institute of Technology,p.","mla":"Blaschko, Matthew, et al. “Semi-Supervised Analysis of Human FMRI Data.” <i>BBCI: Berlin Brain-Computer Interface Workshop - Advances in Neurotechnology</i>, Berlin Institute of Technology, 2009.","chicago":"Blaschko, Matthew, Christoph Lampert, and Andreas Bartels. <i>Semi-Supervised Analysis of Human FMRI Data</i>. <i>BBCI: Berlin Brain-Computer Interface Workshop - Advances in Neurotechnology</i>. Berlin Institute of Technology, 2009."},"publication_status":"published","publication":"BBCI: Berlin Brain-Computer Interface Workshop - Advances in Neurotechnology","date_created":"2018-12-11T12:04:41Z","type":"conference_poster","date_published":"2009-07-10T00:00:00Z","publisher":"Berlin Institute of Technology","status":"public","title":"Semi-supervised analysis of human fMRI data","month":"07","abstract":[{"lang":"eng","text":"Kernel Canonical Correlation Analysis (KCCA) is a general technique for subspace learning that incorporates principal components analysis (PCA) and Fisher linear discriminant analysis (LDA) as special cases. By finding directions that maximize correlation, CCA learns representations tied more closely to underlying process generating the the data and can ignore high-variance noise directions. However, for data where acquisition in a given modality is expensive or otherwise limited, CCA may suffer from small sample effects. We propose to use semisupervised Laplacian regularization to utilize data that are present in only one modality. This approach is able to find highly correlated directions that also lie along the data manifold, resulting in a more robust estimate of correlated subspaces. Functional magnetic resonance imaging (fMRI) acquired data are naturally amenable to subspace techniques as data are well aligned. fMRI data of the human brain are a particularly interesting candidate. In this study we implemented various supervised and semi-supervised versions of CCA on human fMRI data, with regression to single and multivariate labels (corresponding to video content subjects viewed during the image acquisition). In each variate condition, the semi-supervised variants of CCA performed better than the supervised variants, including a supervised variant with Laplacian regularization. We additionally analyze the weights learned by the regression in order to infer brain regions that are important to different types of visual processing."}],"date_updated":"2019-04-26T07:22:33Z","year":"2009","extern":1,"day":"10","author":[{"first_name":"Matthew","last_name":"Blaschko","full_name":"Blaschko,Matthew B"},{"full_name":"Christoph Lampert","orcid":"0000-0001-8622-7887","first_name":"Christoph","last_name":"Lampert","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87"},{"full_name":"Bartels, Andreas","last_name":"Bartels","first_name":"Andreas"}],"_id":"3699"},{"date_published":"2009-09-10T00:00:00Z","type":"conference","date_created":"2018-12-11T12:04:42Z","page":"1 - 11","doi":"10.5244/C.23.63","publication_status":"published","conference":{"name":"BMVC: British Machine Vision Conference"},"citation":{"short":"M. Blaschko, C. Lampert, in:, BMVA Press, 2009, pp. 1–11.","ama":"Blaschko M, Lampert C. Object localization with global and local context kernels. In: BMVA Press; 2009:1-11. doi:<a href=\"https://doi.org/10.5244/C.23.63\">10.5244/C.23.63</a>","ieee":"M. Blaschko and C. Lampert, “Object localization with global and local context kernels,” presented at the BMVC: British Machine Vision Conference, 2009, pp. 1–11.","ista":"Blaschko M, Lampert C. 2009. Object localization with global and local context kernels. BMVC: British Machine Vision Conference, Proceedings of the BMVC, , 1–11.","apa":"Blaschko, M., &#38; Lampert, C. (2009). Object localization with global and local context kernels (pp. 1–11). Presented at the BMVC: British Machine Vision Conference, BMVA Press. <a href=\"https://doi.org/10.5244/C.23.63\">https://doi.org/10.5244/C.23.63</a>","mla":"Blaschko, Matthew, and Christoph Lampert. <i>Object Localization with Global and Local Context Kernels</i>. BMVA Press, 2009, pp. 1–11, doi:<a href=\"https://doi.org/10.5244/C.23.63\">10.5244/C.23.63</a>.","chicago":"Blaschko, Matthew, and Christoph Lampert. “Object Localization with Global and Local Context Kernels,” 1–11. BMVA Press, 2009. <a href=\"https://doi.org/10.5244/C.23.63\">https://doi.org/10.5244/C.23.63</a>."},"quality_controlled":0,"publist_id":"2655","main_file_link":[{"open_access":"0","url":"http://www.bmva.org/bmvc/2009/Papers/Paper228/Paper228.pdf"}],"_id":"3703","author":[{"last_name":"Blaschko","first_name":"Matthew","full_name":"Blaschko,Matthew B"},{"first_name":"Christoph","orcid":"0000-0001-8622-7887","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","last_name":"Lampert","full_name":"Christoph Lampert"}],"extern":1,"year":"2009","day":"10","tmp":{"short":"CC BY (4.0)","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"acknowledgement":"The research leading to these results has received funding from the European Research Council under the European Community’s Seventh Framework Programme (FP7/2007- 2013) / ERC grant agreement no. 228180. This work was funded in part by the EC project CLASS, IST 027978, and the PASCAL2 network of excellence. The first author is supported by the Royal Academy of Engineering through a Newton International Fellowship.","abstract":[{"lang":"eng","text":"Recent research has shown that the use of contextual cues significantly improves performance in sliding window type localization systems. In this work, we propose a method that incorporates both global and local context information through appropriately defined kernel functions. In particular, we make use of a weighted combination of kernels defined over local spatial regions, as well as a global context kernel. The relative importance of the context contributions is learned automatically, and the resulting discriminant function is of a form such that localization at test time can be solved efficiently using a branch and bound optimization scheme. By specifying context directly with a kernel learning approach, we achieve high localization accuracy with a simple and efficient representation. This is in contrast to other systems that incorporate context for which expensive inference needs to be done at test time. We show experimentally on the PASCAL VOC datasets that the inclusion of context can significantly improve localization performance, provided the relative contributions of context cues are learned appropriately."}],"date_updated":"2021-01-12T07:51:36Z","alternative_title":["Proceedings of the BMVC"],"month":"09","title":"Object localization with global and local context kernels","status":"public","publisher":"BMVA Press"},{"publist_id":"2652","quality_controlled":0,"citation":{"ama":"Lampert C, Nickisch H, Harmeling S. Learning to detect unseen object classes by between-class attribute transfer. In: IEEE; 2009:951-958. doi:<a href=\"https://doi.org/10.1109/CVPR.2009.5206594\">10.1109/CVPR.2009.5206594</a>","ieee":"C. Lampert, H. Nickisch, and S. Harmeling, “Learning to detect unseen object classes by between-class attribute transfer,” presented at the CVPR: Computer Vision and Pattern Recognition, 2009, pp. 951–958.","short":"C. Lampert, H. Nickisch, S. Harmeling, in:, IEEE, 2009, pp. 951–958.","chicago":"Lampert, Christoph, Hannes Nickisch, and Stefan Harmeling. “Learning to Detect Unseen Object Classes by Between-Class Attribute Transfer,” 951–58. IEEE, 2009. <a href=\"https://doi.org/10.1109/CVPR.2009.5206594\">https://doi.org/10.1109/CVPR.2009.5206594</a>.","apa":"Lampert, C., Nickisch, H., &#38; Harmeling, S. (2009). Learning to detect unseen object classes by between-class attribute transfer (pp. 951–958). Presented at the CVPR: Computer Vision and Pattern Recognition, IEEE. <a href=\"https://doi.org/10.1109/CVPR.2009.5206594\">https://doi.org/10.1109/CVPR.2009.5206594</a>","mla":"Lampert, Christoph, et al. <i>Learning to Detect Unseen Object Classes by Between-Class Attribute Transfer</i>. IEEE, 2009, pp. 951–58, doi:<a href=\"https://doi.org/10.1109/CVPR.2009.5206594\">10.1109/CVPR.2009.5206594</a>.","ista":"Lampert C, Nickisch H, Harmeling S. 2009. Learning to detect unseen object classes by between-class attribute transfer. CVPR: Computer Vision and Pattern Recognition, 951–958."},"page":"951 - 958","date_created":"2018-12-11T12:04:43Z","doi":"10.1109/CVPR.2009.5206594","conference":{"name":"CVPR: Computer Vision and Pattern Recognition"},"publication_status":"published","date_published":"2009-06-20T00:00:00Z","type":"conference","title":"Learning to detect unseen object classes by between-class attribute transfer","status":"public","publisher":"IEEE","month":"06","year":"2009","extern":1,"day":"20","acknowledgement":"This work was funded in part by the EC project CLASS, IST 027978, and the PASCAL2 network of excellence.","abstract":[{"lang":"eng","text":"We study the problem of object classification when training and test classes are disjoint, i.e. no training examples of the target classes are available. This setup has hardly been studied in computer vision research, but it is the rule rather than the exception, because the world contains tens of thousands of different object classes and for only a very few of them image, collections have been formed and annotated with suitable class labels. In this paper, we tackle the problem by introducing attribute-based classification. It performs object detection based on a human-specified high-level description of the target objects instead of training images. The description consists of arbitrary semantic attributes, like shape, color or even geographic information. Because such properties transcend the specific learning task at hand, they can be pre-learned, e.g. from image datasets unrelated to the current task. Afterwards, new classes can be detected based on their attribute representation, without the need for a new training phase. In order to evaluate our method and to facilitate research in this area, we have assembled a new large-scale dataset, ldquoAnimals with Attributesrdquo, of over 30,000 animal images that match the 50 classes in Osherson‘s classic table of how strongly humans associate 85 semantic attributes with animal classes. Our experiments show that by using an attribute layer it is indeed possible to build a learning object detection system that does not require any training images of the target classes."}],"date_updated":"2021-01-12T07:51:36Z","_id":"3704","author":[{"full_name":"Christoph Lampert","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","last_name":"Lampert","orcid":"0000-0001-8622-7887","first_name":"Christoph"},{"full_name":"Nickisch,Hannes","first_name":"Hannes","last_name":"Nickisch"},{"last_name":"Harmeling","first_name":"Stefan","full_name":"Harmeling,Stefan"}]},{"oa_version":"None","type":"book","language":[{"iso":"eng"}],"date_published":"2009-09-03T00:00:00Z","publication_status":"published","doi":"10.1561/0600000027","date_created":"2018-12-11T12:04:44Z","page":"112","intvolume":"         4","citation":{"apa":"Lampert, C. (2009). <i>Kernel Methods in Computer Vision</i> (Vol. 4). now publishers. <a href=\"https://doi.org/10.1561/0600000027\">https://doi.org/10.1561/0600000027</a>","mla":"Lampert, Christoph. <i>Kernel Methods in Computer Vision</i>. Vol. 4, now publishers, 2009, doi:<a href=\"https://doi.org/10.1561/0600000027\">10.1561/0600000027</a>.","ista":"Lampert C. 2009. Kernel Methods in Computer Vision, now publishers, 112p.","chicago":"Lampert, Christoph. <i>Kernel Methods in Computer Vision</i>. Vol. 4. now publishers, 2009. <a href=\"https://doi.org/10.1561/0600000027\">https://doi.org/10.1561/0600000027</a>.","short":"C. Lampert, Kernel Methods in Computer Vision, now publishers, 2009.","ama":"Lampert C. <i>Kernel Methods in Computer Vision</i>. Vol 4. now publishers; 2009. doi:<a href=\"https://doi.org/10.1561/0600000027\">10.1561/0600000027</a>","ieee":"C. Lampert, <i>Kernel Methods in Computer Vision</i>, vol. 4. now publishers, 2009."},"quality_controlled":"1","volume":4,"publist_id":"2651","article_processing_charge":"No","author":[{"full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","last_name":"Lampert","first_name":"Christoph","orcid":"0000-0001-8622-7887"}],"_id":"3707","date_updated":"2021-12-21T15:38:43Z","abstract":[{"text":"Over the last years, kernel methods have established themselves as powerful tools for computer vision researchers as well as for practitioners. In this tutorial, we give an introduction to kernel methods in computer vision from a geometric perspective, introducing not only the ubiquitous support vector machines, but also less known techniques for regression, dimensionality reduction, outlier detection and clustering. Additionally, we give an outlook on very recent, non-classical techniques for the prediction of structure data, for the estimation of statistical dependency and for learning the kernel function itself. All methods are illustrated with examples of successful application from the recent computer vision research literature.","lang":"eng"}],"day":"03","extern":"1","year":"2009","month":"09","alternative_title":["Foundations and Trends® in Computer Graphics and Vision"],"status":"public","publisher":"now publishers","user_id":"8b945eb4-e2f2-11eb-945a-df72226e66a9","title":"Kernel Methods in Computer Vision","publication_identifier":{"isbn":["978-1-60198-268-1"],"eisbn":["978-1-60198-269-8"]}},{"publist_id":"2649","citation":{"short":"S. Nowozin, C. Lampert, in:, IEEE, 2009, pp. 818–825.","ama":"Nowozin S, Lampert C. Global connectivity potentials for random field models. In: IEEE; 2009:818-825. doi:<a href=\"https://doi.org/10.1109/CVPR.2009.5206567\">10.1109/CVPR.2009.5206567</a>","ieee":"S. Nowozin and C. Lampert, “Global connectivity potentials for random field models,” presented at the CVPR: Computer Vision and Pattern Recognition, 2009, pp. 818–825.","chicago":"Nowozin, Sebastian, and Christoph Lampert. “Global Connectivity Potentials for Random Field Models,” 818–25. IEEE, 2009. <a href=\"https://doi.org/10.1109/CVPR.2009.5206567\">https://doi.org/10.1109/CVPR.2009.5206567</a>.","apa":"Nowozin, S., &#38; Lampert, C. (2009). Global connectivity potentials for random field models (pp. 818–825). Presented at the CVPR: Computer Vision and Pattern Recognition, IEEE. <a href=\"https://doi.org/10.1109/CVPR.2009.5206567\">https://doi.org/10.1109/CVPR.2009.5206567</a>","ista":"Nowozin S, Lampert C. 2009. Global connectivity potentials for random field models. CVPR: Computer Vision and Pattern Recognition, 818–825.","mla":"Nowozin, Sebastian, and Christoph Lampert. <i>Global Connectivity Potentials for Random Field Models</i>. IEEE, 2009, pp. 818–25, doi:<a href=\"https://doi.org/10.1109/CVPR.2009.5206567\">10.1109/CVPR.2009.5206567</a>."},"quality_controlled":0,"date_created":"2018-12-11T12:04:44Z","page":"818 - 825","doi":"10.1109/CVPR.2009.5206567","conference":{"name":"CVPR: Computer Vision and Pattern Recognition"},"publication_status":"published","date_published":"2009-06-20T00:00:00Z","type":"conference","title":"Global connectivity potentials for random field models","status":"public","publisher":"IEEE","month":"06","extern":1,"year":"2009","day":"20","abstract":[{"text":"Markov random field (MRF, CRF) models are popular in computer vision. However, in order to be computationally tractable they are limited to incorporate only local interactions and cannot model global properties, such as connectedness, which is a potentially useful high-level prior for object segmentation. In this work, we overcome this limitation by deriving a potential function that enforces the output labeling to be connected and that can naturally be used in the framework of recent MAP-MRF LP relaxations. Using techniques from polyhedral combinatorics, we show that a provably tight approximation to the MAP solution of the resulting MRF can still be found efficiently by solving a sequence of max-flow problems. The efficiency of the inference procedure also allows us to learn the parameters of a MRF with global connectivity potentials by means of a cutting plane algorithm. We experimentally evaluate our algorithm on both synthetic data and on the challenging segmentation task of the PASCAL VOC 2008 data set. We show that in both cases the addition of a connectedness prior significantly reduces the segmentation error.","lang":"eng"}],"acknowledgement":"Conference Information URL:\n\nhttp://www.cvpr2009.org/","date_updated":"2021-01-12T07:51:38Z","_id":"3708","author":[{"last_name":"Nowozin","first_name":"Sebastian","full_name":"Nowozin, Sebastian"},{"full_name":"Christoph Lampert","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","last_name":"Lampert","first_name":"Christoph","orcid":"0000-0001-8622-7887"}]},{"title":"Detecting objects in large image collections and videos by efficient subimage retrieval","publisher":"IEEE","status":"public","month":"09","year":"2009","extern":1,"day":"29","abstract":[{"lang":"eng","text":"We study the task of detecting the occurrence of objects in large image collections or in videos, a problem that combines aspects of content based image retrieval and object localization. While most previous approaches are either limited to special kinds of queries, or do not scale to large image sets, we propose a new method, efficient subimage retrieval (ESR), which is at the same time very flexible and very efficient. Relying on a two-layered branch-and-bound setup, ESR performs object-based image retrieval in sets of 100,000 or more images within seconds. An extensive evaluation on several datasets shows that ESR is not only very fast, but it also achieves detection accuracies that are on par with or superior to previously published methods for object-based image retrieval."}],"acknowledgement":"Conference Information URL:\n\nhttp://www.iccv2009.org/","date_updated":"2021-01-12T07:51:38Z","_id":"3709","author":[{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","last_name":"Lampert","orcid":"0000-0001-8622-7887","first_name":"Christoph","full_name":"Christoph Lampert"}],"publist_id":"2647","citation":{"mla":"Lampert, Christoph. <i>Detecting Objects in Large Image Collections and Videos by Efficient Subimage Retrieval</i>. IEEE, 2009, pp. 987–94, doi:<a href=\"https://doi.org/10.1109/ICCV.2009.5459359\">10.1109/ICCV.2009.5459359</a>.","ista":"Lampert C. 2009. Detecting objects in large image collections and videos by efficient subimage retrieval. ICCV: International Conference on Computer Vision, 987–994.","apa":"Lampert, C. (2009). Detecting objects in large image collections and videos by efficient subimage retrieval (pp. 987–994). Presented at the ICCV: International Conference on Computer Vision, IEEE. <a href=\"https://doi.org/10.1109/ICCV.2009.5459359\">https://doi.org/10.1109/ICCV.2009.5459359</a>","chicago":"Lampert, Christoph. “Detecting Objects in Large Image Collections and Videos by Efficient Subimage Retrieval,” 987–94. IEEE, 2009. <a href=\"https://doi.org/10.1109/ICCV.2009.5459359\">https://doi.org/10.1109/ICCV.2009.5459359</a>.","short":"C. Lampert, in:, IEEE, 2009, pp. 987–994.","ieee":"C. Lampert, “Detecting objects in large image collections and videos by efficient subimage retrieval,” presented at the ICCV: International Conference on Computer Vision, 2009, pp. 987–994.","ama":"Lampert C. Detecting objects in large image collections and videos by efficient subimage retrieval. In: IEEE; 2009:987-994. doi:<a href=\"https://doi.org/10.1109/ICCV.2009.5459359\">10.1109/ICCV.2009.5459359</a>"},"quality_controlled":0,"date_created":"2018-12-11T12:04:44Z","page":"987 - 994","doi":"10.1109/ICCV.2009.5459359","publication_status":"published","conference":{"name":"ICCV: International Conference on Computer Vision"},"date_published":"2009-09-29T00:00:00Z","type":"conference"},{"date_published":"2009-12-01T00:00:00Z","type":"journal_article","page":"2129 - 2142","date_created":"2018-12-11T12:04:45Z","publication":"IEEE Transactions on Pattern Analysis and Machine Intelligence","publication_status":"published","doi":"10.1109/TPAMI.2009.144","citation":{"short":"C. Lampert, M. Blaschko, T. Hofmann, IEEE Transactions on Pattern Analysis and Machine Intelligence 31 (2009) 2129–2142.","ama":"Lampert C, Blaschko M, Hofmann T. Efficient subwindow search: A branch and bound framework for object localization. <i>IEEE Transactions on Pattern Analysis and Machine Intelligence</i>. 2009;31(12):2129-2142. doi:<a href=\"https://doi.org/10.1109/TPAMI.2009.144\">10.1109/TPAMI.2009.144</a>","ieee":"C. Lampert, M. Blaschko, and T. Hofmann, “Efficient subwindow search: A branch and bound framework for object localization,” <i>IEEE Transactions on Pattern Analysis and Machine Intelligence</i>, vol. 31, no. 12. IEEE, pp. 2129–2142, 2009.","chicago":"Lampert, Christoph, Matthew Blaschko, and Thomas Hofmann. “Efficient Subwindow Search: A Branch and Bound Framework for Object Localization.” <i>IEEE Transactions on Pattern Analysis and Machine Intelligence</i>. IEEE, 2009. <a href=\"https://doi.org/10.1109/TPAMI.2009.144\">https://doi.org/10.1109/TPAMI.2009.144</a>.","mla":"Lampert, Christoph, et al. “Efficient Subwindow Search: A Branch and Bound Framework for Object Localization.” <i>IEEE Transactions on Pattern Analysis and Machine Intelligence</i>, vol. 31, no. 12, IEEE, 2009, pp. 2129–42, doi:<a href=\"https://doi.org/10.1109/TPAMI.2009.144\">10.1109/TPAMI.2009.144</a>.","ista":"Lampert C, Blaschko M, Hofmann T. 2009. Efficient subwindow search: A branch and bound framework for object localization. IEEE Transactions on Pattern Analysis and Machine Intelligence. 31(12), 2129–2142.","apa":"Lampert, C., Blaschko, M., &#38; Hofmann, T. (2009). Efficient subwindow search: A branch and bound framework for object localization. <i>IEEE Transactions on Pattern Analysis and Machine Intelligence</i>. IEEE. <a href=\"https://doi.org/10.1109/TPAMI.2009.144\">https://doi.org/10.1109/TPAMI.2009.144</a>"},"intvolume":"        31","quality_controlled":0,"volume":31,"publist_id":"2648","main_file_link":[{"url":"http://www2.computer.org/portal/web/csdl/doi/10.1109/TPAMI.2009.144","open_access":"0"}],"_id":"3710","author":[{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","last_name":"Lampert","first_name":"Christoph","orcid":"0000-0001-8622-7887","full_name":"Christoph Lampert"},{"last_name":"Blaschko","first_name":"Matthew","full_name":"Blaschko,Matthew B"},{"full_name":"Hofmann,Thomas","first_name":"Thomas","last_name":"Hofmann"}],"day":"01","year":"2009","extern":1,"date_updated":"2021-01-12T07:51:39Z","abstract":[{"lang":"eng","text":"Most successful object recognition systems rely on binary classification, deciding only if an object is present or not, but not providing information on the actual object location. To estimate the object‘s location, one can take a sliding window approach, but this strongly increases the computational cost because the classifier or similarity function has to be evaluated over a large set of candidate subwindows. In this paper, we propose a simple yet powerful branch and bound scheme that allows efficient maximization of a large class of quality functions over all possible subimages. It converges to a globally optimal solution typically in linear or even sublinear time, in contrast to the quadratic scaling of exhaustive or sliding window search. We show how our method is applicable to different object detection and image retrieval scenarios. The achieved speedup allows the use of classifiers for localization that formerly were considered too slow for this task, such as SVMs with a spatial pyramid kernel or nearest-neighbor classifiers based on the chi^2 distance. We demonstrate state-of-the-art localization performance of the resulting systems on the UIUC Cars data set, the PASCAL VOC 2006 data set, and in the PASCAL VOC 2007 competition."}],"acknowledgement":"This work was funded in part by the EU projects CLASS, IST 027978, and PerAct, EST 504321. ","issue":"12","month":"12","title":"Efficient subwindow search: A branch and bound framework for object localization","status":"public","publisher":"IEEE"},{"publist_id":"2645","main_file_link":[{"open_access":"0","url":"http://www.nowozin.net/sebastian/papers/dhillon2008actionclassification.pdf"}],"quality_controlled":0,"citation":{"ista":"Dhillon P, Nowozin S, Lampert C. 2009. Combining appearance and motion for human action classification in videos. CVPR: Computer Vision and Pattern Recognition, 22–29.","mla":"Dhillon, Paramveer, et al. <i>Combining Appearance and Motion for Human Action Classification in Videos</i>. IEEE, 2009, pp. 22–29, doi:<a href=\"https://doi.org/10.1109/CVPRW.2009.5204237\">10.1109/CVPRW.2009.5204237</a>.","apa":"Dhillon, P., Nowozin, S., &#38; Lampert, C. (2009). Combining appearance and motion for human action classification in videos (pp. 22–29). Presented at the CVPR: Computer Vision and Pattern Recognition, IEEE. <a href=\"https://doi.org/10.1109/CVPRW.2009.5204237\">https://doi.org/10.1109/CVPRW.2009.5204237</a>","chicago":"Dhillon, Paramveer, Sebastian Nowozin, and Christoph Lampert. “Combining Appearance and Motion for Human Action Classification in Videos,” 22–29. IEEE, 2009. <a href=\"https://doi.org/10.1109/CVPRW.2009.5204237\">https://doi.org/10.1109/CVPRW.2009.5204237</a>.","short":"P. Dhillon, S. Nowozin, C. Lampert, in:, IEEE, 2009, pp. 22–29.","ieee":"P. Dhillon, S. Nowozin, and C. Lampert, “Combining appearance and motion for human action classification in videos,” presented at the CVPR: Computer Vision and Pattern Recognition, 2009, pp. 22–29.","ama":"Dhillon P, Nowozin S, Lampert C. Combining appearance and motion for human action classification in videos. In: IEEE; 2009:22-29. doi:<a href=\"https://doi.org/10.1109/CVPRW.2009.5204237\">10.1109/CVPRW.2009.5204237</a>"},"publication_status":"published","conference":{"name":"CVPR: Computer Vision and Pattern Recognition"},"doi":"10.1109/CVPRW.2009.5204237","date_created":"2018-12-11T12:04:45Z","page":"22 - 29","type":"conference","date_published":"2009-08-18T00:00:00Z","publisher":"IEEE","status":"public","title":"Combining appearance and motion for human action classification in videos","month":"08","date_updated":"2021-01-12T07:51:39Z","abstract":[{"text":"An important cue to high level scene understanding is to analyze the objects in the scene and their behavior and interactions. In this paper, we study the problem of classification of activities in videos, as this is an integral component of any scene understanding system, and present a novel approach for recognizing human action categories in videos by combining information from appearance and motion of human body parts. Our approach is based on tracking human body parts by using mixture particle filters and then clustering the particles using local non - parametric clustering, hence associating a local set of particles to each cluster mode. The trajectory of these cluster modes provides the ldquomotionrdquo information and the ldquoappearancerdquo information is provided by the statistical information about the relative motion of these local set of particles over a number of frames. Later we use a ldquoBag of Wordsrdquo model to build one histogram per video sequence from the set of these robust appearance and motion descriptors. These histograms provide us characteristic information which helps us to discriminate among various human actions which ultimately helps us in better understanding of the complete scene. We tested our approach on the standard KTH and Weizmann human action datasets and the results were comparable to the state of the art methods. Additionally our approach is able to distinguish between activities that involve the motion of complete body from those in which only certain body parts move. In other words, our method discriminates well between activities with ldquoglobal body motionrdquo like running, jogging etc. and ldquolocal motionrdquo like waving, boxing etc.","lang":"eng"}],"day":"18","year":"2009","extern":1,"author":[{"full_name":"Dhillon, Paramveer S","last_name":"Dhillon","first_name":"Paramveer"},{"full_name":"Nowozin, Sebastian","first_name":"Sebastian","last_name":"Nowozin"},{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","last_name":"Lampert","orcid":"0000-0001-8622-7887","first_name":"Christoph","full_name":"Christoph Lampert"}],"_id":"3711"},{"status":"public","publisher":"Springer","title":"Active structured learning for high-speed object detection","alternative_title":["LNCS"],"month":"10","acknowledgement":"This work was funded in part by the EU project CLASS, IST 027978.\nConference Information URL: http://www.optecnet.de/veranstaltungen/2009/09/dagm-2009/","abstract":[{"text":"High-speed smooth and accurate visual tracking of objects in arbitrary, unstructured environments is essential for robotics and human motion analysis. However, building a system that can adapt to arbitrary objects and a wide range of lighting conditions is a challenging problem, especially if hard real-time constraints apply like in robotics scenarios. In this work, we introduce a method for learning a discriminative object tracking system based on the recent structured regression framework for object localization. Using a kernel function that allows fast evaluation on the GPU, the resulting system can process video streams at speed of 100 frames per second or more. Consecutive frames in high speed video sequences are typically very redundant, and for training an object detection system, it is sufficient to have training labels from only a subset of all images. We propose an active learning method that select training examples in a data-driven way, thereby minimizing the required number of training labeling. Experiments on realistic data show that the active learning is superior to previously used methods for dataset subsampling for this task.","lang":"eng"}],"date_updated":"2021-01-12T07:51:41Z","year":"2009","extern":1,"day":"07","author":[{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","last_name":"Lampert","orcid":"0000-0001-8622-7887","first_name":"Christoph","full_name":"Christoph Lampert"},{"full_name":"Peters, Jan","last_name":"Peters","first_name":"Jan"}],"_id":"3715","publist_id":"2642","volume":5748,"quality_controlled":0,"intvolume":"      5748","citation":{"mla":"Lampert, Christoph, and Jan Peters. <i>Active Structured Learning for High-Speed Object Detection</i>. Vol. 5748, Springer, 2009, pp. 221–31, doi:<a href=\"https://doi.org/10.1007/978-3-642-03798-6_23\">10.1007/978-3-642-03798-6_23</a>.","ista":"Lampert C, Peters J. 2009. Active structured learning for high-speed object detection. DAGM: German Association For Pattern Recognition, LNCS, vol. 5748, 221–231.","apa":"Lampert, C., &#38; Peters, J. (2009). Active structured learning for high-speed object detection (Vol. 5748, pp. 221–231). Presented at the DAGM: German Association For Pattern Recognition, Springer. <a href=\"https://doi.org/10.1007/978-3-642-03798-6_23\">https://doi.org/10.1007/978-3-642-03798-6_23</a>","chicago":"Lampert, Christoph, and Jan Peters. “Active Structured Learning for High-Speed Object Detection,” 5748:221–31. Springer, 2009. <a href=\"https://doi.org/10.1007/978-3-642-03798-6_23\">https://doi.org/10.1007/978-3-642-03798-6_23</a>.","short":"C. Lampert, J. Peters, in:, Springer, 2009, pp. 221–231.","ieee":"C. Lampert and J. Peters, “Active structured learning for high-speed object detection,” presented at the DAGM: German Association For Pattern Recognition, 2009, vol. 5748, pp. 221–231.","ama":"Lampert C, Peters J. Active structured learning for high-speed object detection. In: Vol 5748. Springer; 2009:221-231. doi:<a href=\"https://doi.org/10.1007/978-3-642-03798-6_23\">10.1007/978-3-642-03798-6_23</a>"},"doi":"10.1007/978-3-642-03798-6_23","publication_status":"published","conference":{"name":"DAGM: German Association For Pattern Recognition"},"date_created":"2018-12-11T12:04:46Z","page":"221 - 231","type":"conference","date_published":"2009-10-07T00:00:00Z"},{"main_file_link":[{"open_access":"0","url":"http://pubman.mpdl.mpg.de/pubman/faces/viewItemOverviewPage.jsp?itemId=escidoc:1789154"}],"publist_id":"2640","quality_controlled":0,"citation":{"chicago":"Lampert, Christoph, and Jan Peters. <i>A High-Speed Object Tracker from off-the-Shelf Components</i>. <i>ICCV: International Conference on Computer Vision</i>. IEEE, 2009.","mla":"Lampert, Christoph, and Jan Peters. “A High-Speed Object Tracker from off-the-Shelf Components.” <i>ICCV: International Conference on Computer Vision</i>, IEEE, 2009.","apa":"Lampert, C., &#38; Peters, J. (2009). <i>A high-speed object tracker from off-the-shelf components</i>. <i>ICCV: International Conference on Computer Vision</i>. IEEE.","ista":"Lampert C, Peters J. 2009. A high-speed object tracker from off-the-shelf components, IEEE,p.","short":"C. Lampert, J. Peters, A High-Speed Object Tracker from off-the-Shelf Components, IEEE, 2009.","ieee":"C. Lampert and J. Peters, <i>A high-speed object tracker from off-the-shelf components</i>. IEEE, 2009.","ama":"Lampert C, Peters J. <i>A High-Speed Object Tracker from off-the-Shelf Components</i>. IEEE; 2009."},"date_created":"2018-12-11T12:04:47Z","publication":"ICCV: International Conference on Computer Vision","publication_status":"published","date_published":"2009-09-27T00:00:00Z","type":"conference_poster","title":"A high-speed object tracker from off-the-shelf components","publisher":"IEEE","status":"public","month":"09","tmp":{"short":"CC BY (4.0)","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"day":"27","year":"2009","extern":1,"date_updated":"2020-07-14T12:46:14Z","abstract":[{"text":"We introduce RTblob, an open-source real-time vision system for 3D object detection that achieves over 200 Hz tracking speed with only off-the-shelf hardware component. It allows fast and accurate tracking of colored objects in 3D without expensive and often custom-built hardware, instead making use of the PC graphics cards for the necessary image processing operations.","lang":"eng"}],"acknowledgement":"IEEE Workshop URL:  http://humanoidscv.ime.cmc.osaka-u.ac.jp/","_id":"3717","author":[{"full_name":"Christoph Lampert","last_name":"Lampert","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","first_name":"Christoph","orcid":"0000-0001-8622-7887"},{"full_name":"Peters, Jan","first_name":"Jan","last_name":"Peters"}]},{"author":[{"full_name":"Gasper Tkacik","id":"3D494DCA-F248-11E8-B48F-1D18A9856A87","last_name":"Tkacik","first_name":"Gasper","orcid":"0000-0002-6699-1455"},{"full_name":"Schneidman, Elad","first_name":"Elad","last_name":"Schneidman"},{"full_name":"Berry, Michael J","last_name":"Berry","first_name":"Michael"},{"full_name":"Bialek, William S","first_name":"William","last_name":"Bialek"}],"_id":"3732","date_updated":"2021-01-12T07:51:48Z","abstract":[{"lang":"eng","text":"Ising models with pairwise interactions are the least structured, or maximum-entropy, probability distributions that exactly reproduce measured pairwise correlations between spins. Here we use this equivalence to construct Ising models that describe the correlated spiking activity of populations of 40 neurons in the salamander retina responding to natural movies. We show that pairwise interactions between neurons account for observed higher-order correlations, and that for groups of 10 or more neurons pairwise interactions can no longer be regarded as small perturbations in an independent system. We then construct network ensembles that generalize the network instances observed in the experiment, and study their thermodynamic behavior and coding capacity. Based on this construction, we can also create synthetic networks of 120 neurons, and find that with increasing size the networks operate closer to a critical point and start exhibiting collective behaviors reminiscent of spin glasses. We examine closely two such behaviors that could be relevant for neural code: tuning of the network to the critical point to maximize the ability to encode diverse stimuli, and using the metastable states of the Ising Hamiltonian as neural code words."}],"day":"01","year":"2009","extern":1,"month":"01","publisher":"ArXiv","status":"public","title":"Spin glass models for a network of real neurons","oa":1,"type":"preprint","date_published":"2009-01-01T00:00:00Z","publication_status":"published","date_created":"2018-12-11T12:04:52Z","publication":"ArXiv","volume":"q-bio.NC","citation":{"ieee":"G. Tkačik, E. Schneidman, M. Berry, and W. Bialek, “Spin glass models for a network of real neurons,” <i>ArXiv</i>, vol. q-NC. ArXiv, 2009.","ama":"Tkačik G, Schneidman E, Berry M, Bialek W. Spin glass models for a network of real neurons. <i>ArXiv</i>. 2009;q-NC.","short":"G. Tkačik, E. Schneidman, M. Berry, W. Bialek, ArXiv q-NC (2009).","apa":"Tkačik, G., Schneidman, E., Berry, M., &#38; Bialek, W. (2009). Spin glass models for a network of real neurons. <i>ArXiv</i>. ArXiv.","mla":"Tkačik, Gašper, et al. “Spin Glass Models for a Network of Real Neurons.” <i>ArXiv</i>, vol. q-NC, ArXiv, 2009.","ista":"Tkačik G, Schneidman E, Berry M, Bialek W. 2009. Spin glass models for a network of real neurons. ArXiv, q-NC, .","chicago":"Tkačik, Gašper, Elad Schneidman, Michael Berry, and William Bialek. “Spin Glass Models for a Network of Real Neurons.” <i>ArXiv</i>. ArXiv, 2009."},"quality_controlled":0,"main_file_link":[{"open_access":"1","url":"http://arxiv.org/abs/0912.5409v1"}],"publist_id":"2496"},{"date_published":"2009-01-01T00:00:00Z","type":"journal_article","publication":"PNAS","page":"18638 - 18643","date_created":"2018-12-11T12:04:52Z","doi":"10.1073/pnas.0905497106","publication_status":"published","quality_controlled":0,"citation":{"chicago":"Kryazhimskiy, Sergey, Gašper Tkačik, and Joshua Plotkin. “The Dynamics of Adaptation on Correlated Fitness Landscapes.” <i>PNAS</i>. National Academy of Sciences, 2009. <a href=\"https://doi.org/10.1073/pnas.0905497106\">https://doi.org/10.1073/pnas.0905497106</a>.","apa":"Kryazhimskiy, S., Tkačik, G., &#38; Plotkin, J. (2009). The dynamics of adaptation on correlated fitness landscapes. <i>PNAS</i>. National Academy of Sciences. <a href=\"https://doi.org/10.1073/pnas.0905497106\">https://doi.org/10.1073/pnas.0905497106</a>","ista":"Kryazhimskiy S, Tkačik G, Plotkin J. 2009. The dynamics of adaptation on correlated fitness landscapes. PNAS. 106(44), 18638–18643.","mla":"Kryazhimskiy, Sergey, et al. “The Dynamics of Adaptation on Correlated Fitness Landscapes.” <i>PNAS</i>, vol. 106, no. 44, National Academy of Sciences, 2009, pp. 18638–43, doi:<a href=\"https://doi.org/10.1073/pnas.0905497106\">10.1073/pnas.0905497106</a>.","ieee":"S. Kryazhimskiy, G. Tkačik, and J. Plotkin, “The dynamics of adaptation on correlated fitness landscapes,” <i>PNAS</i>, vol. 106, no. 44. National Academy of Sciences, pp. 18638–18643, 2009.","ama":"Kryazhimskiy S, Tkačik G, Plotkin J. The dynamics of adaptation on correlated fitness landscapes. <i>PNAS</i>. 2009;106(44):18638-18643. doi:<a href=\"https://doi.org/10.1073/pnas.0905497106\">10.1073/pnas.0905497106</a>","short":"S. Kryazhimskiy, G. Tkačik, J. Plotkin, PNAS 106 (2009) 18638–18643."},"intvolume":"       106","volume":106,"main_file_link":[{"url":"http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2767361","open_access":"0"}],"publist_id":"2497","_id":"3733","author":[{"first_name":"Sergey","last_name":"Kryazhimskiy","full_name":"Kryazhimskiy,Sergey"},{"id":"3D494DCA-F248-11E8-B48F-1D18A9856A87","last_name":"Tkacik","first_name":"Gasper","orcid":"0000-0002-6699-1455","full_name":"Gasper Tkacik"},{"last_name":"Plotkin","first_name":"Joshua","full_name":"Plotkin,Joshua B"}],"extern":1,"year":"2009","day":"01","issue":"44","abstract":[{"text":"Evolutionary theory predicts that a population in a new environment will accumulate adaptive substitutions, but precisely how they accumulate is poorly understood. The dynamics of adaptation depend on the underlying fitness landscape. Virtually nothing is known about fitness landscapes in nature, and few methods allow us to infer the landscape from empirical data. With a view toward this inference problem, we have developed a theory that, in the weak-mutation limit, predicts how a population's mean fitness and the number of accumulated substitutions are expected to increase over time, depending on the underlying fitness landscape. We find that fitness and substitution trajectories depend not on the full distribution of fitness effects of available mutations but rather on the expected fixation probability and the expected fitness increment of mutations. We introduce a scheme that classifies landscapes in terms of the qualitative evolutionary dynamics they produce. We show that linear substitution trajectories, long considered the hallmark of neutral evolution, can arise even when mutations are strongly selected. Our results provide a basis for understanding the dynamics of adaptation and for inferring properties of an organism's fitness landscape from temporal data. Applying these methods to data from a long-term experiment, we infer the sign and strength of epistasis among beneficial mutations in the Escherichia coli genome.","lang":"eng"}],"date_updated":"2021-01-12T07:51:48Z","month":"01","title":"The dynamics of adaptation on correlated fitness landscapes","status":"public","publisher":"National Academy of Sciences"},{"_id":"3737","author":[{"first_name":"Gasper","orcid":"0000-0002-6699-1455","id":"3D494DCA-F248-11E8-B48F-1D18A9856A87","last_name":"Tkacik","full_name":"Gasper Tkacik"},{"first_name":"Aleksandra","last_name":"Walczak","full_name":"Walczak, Aleksandra M"},{"full_name":"Bialek, William S","last_name":"Bialek","first_name":"William"}],"year":"2009","extern":1,"day":"29","abstract":[{"lang":"eng","text":"In order to survive, reproduce, and (in multicellular organisms) differentiate, cells must control the concentrations of the myriad different proteins that are encoded in the genome. The precision of this control is limited by the inevitable randomness of individual molecular events. Here we explore how cells can maximize their control power in the presence of these physical limits; formally, we solve the theoretical problem of maximizing the information transferred from inputs to outputs when the number of available molecules is held fixed. We start with the simplest version of the problem, in which a single transcription factor protein controls the readout of one or more genes by binding to DNA. We further simplify by assuming that this regulatory network operates in steady state, that the noise is small relative to the available dynamic range, and that the target genes do not interact. Even in this simple limit, we find a surprisingly rich set of optimal solutions. Importantly, for each locally optimal regulatory network, all parameters are determined once the physical constraints on the number of available molecules are specified. Although we are solving an oversimplified version of the problem facing real cells, we see parallels between the structure of these optimal solutions and the behavior of actual genetic regulatory networks. Subsequent papers will discuss more complete versions of the problem."}],"issue":"3 ","date_updated":"2021-01-12T07:51:50Z","month":"09","title":"Optimizing information flow in small genetic networks","status":"public","publisher":"American Institute of Physics","date_published":"2009-09-29T00:00:00Z","type":"journal_article","publication":"Physical Review E Statistical Nonlinear and Soft Matter Physics","date_created":"2018-12-11T12:04:53Z","doi":"10.1103/PhysRevE.80.031920","publication_status":"published","quality_controlled":0,"intvolume":"        80","citation":{"chicago":"Tkačik, Gašper, Aleksandra Walczak, and William Bialek. “Optimizing Information Flow in Small Genetic Networks.” <i>Physical Review E Statistical Nonlinear and Soft Matter Physics</i>. American Institute of Physics, 2009. <a href=\"https://doi.org/10.1103/PhysRevE.80.031920\">https://doi.org/10.1103/PhysRevE.80.031920</a>.","ista":"Tkačik G, Walczak A, Bialek W. 2009. Optimizing information flow in small genetic networks. Physical Review E Statistical Nonlinear and Soft Matter Physics. 80(3).","apa":"Tkačik, G., Walczak, A., &#38; Bialek, W. (2009). Optimizing information flow in small genetic networks. <i>Physical Review E Statistical Nonlinear and Soft Matter Physics</i>. American Institute of Physics. <a href=\"https://doi.org/10.1103/PhysRevE.80.031920\">https://doi.org/10.1103/PhysRevE.80.031920</a>","mla":"Tkačik, Gašper, et al. “Optimizing Information Flow in Small Genetic Networks.” <i>Physical Review E Statistical Nonlinear and Soft Matter Physics</i>, vol. 80, no. 3, American Institute of Physics, 2009, doi:<a href=\"https://doi.org/10.1103/PhysRevE.80.031920\">10.1103/PhysRevE.80.031920</a>.","ama":"Tkačik G, Walczak A, Bialek W. Optimizing information flow in small genetic networks. <i>Physical Review E Statistical Nonlinear and Soft Matter Physics</i>. 2009;80(3). doi:<a href=\"https://doi.org/10.1103/PhysRevE.80.031920\">10.1103/PhysRevE.80.031920</a>","ieee":"G. Tkačik, A. Walczak, and W. Bialek, “Optimizing information flow in small genetic networks,” <i>Physical Review E Statistical Nonlinear and Soft Matter Physics</i>, vol. 80, no. 3. American Institute of Physics, 2009.","short":"G. Tkačik, A. Walczak, W. Bialek, Physical Review E Statistical Nonlinear and Soft Matter Physics 80 (2009)."},"volume":80,"publist_id":"2493","main_file_link":[{"open_access":"0","url":"http://arxiv.org/abs/0903.4491"}]}]