The Experts below are selected from a list of 95124 Experts worldwide ranked by ideXlab platform
Lior Wolf - One of the best experts on this subject based on the ideXlab platform.
-
Temporal Tessellation: A Unified Approach for Video Analysis
International Conference on Computer Vision (ICCV), 2017Co-Authors: Dotan Kaufman, Gil Levi, Tal Hassner, Lior WolfAbstract:We present a general approach to Video understanding, inspired by semantic transfer techniques that have been successfully used for 2D image analysis. Our method considers a Video to be a 1D sequence of clips, each one associated with its own semantics. The nature of these semantics -- natural language captions or other labels -- depends on the task at hand. A Test Video is processed by forming correspondences between its clips and the clips of reference Videos with known semantics, following which, reference semantics can be transferred to the Test Video. We describe two matching methods, both designed to ensure that (a) reference clips appear similar to Test clips and (b), taken together, the semantics of the selected reference clips is consistent and maintains temporal coherence. We use our method for Video captioning on the LSMDC'16 benchmark, Video summarization on the SumMe and TVSum benchmarks, Temporal Action Detection on the Thumos2014 benchmark, and sound prediction on the GreaTest Hits benchmark. Our method not only surpasses the state of the art, in four out of five benchmarks, but importantly, it is the only single method we know of that was successfully applied to such a diverse range of tasks.
-
ICCV - Temporal Tessellation: A Unified Approach for Video Analysis
2017 IEEE International Conference on Computer Vision (ICCV), 2017Co-Authors: Dotan Kaufman, Gil Levi, Tal Hassner, Lior WolfAbstract:We present a general approach to Video understanding, inspired by semantic transfer techniques that have been successfully used for 2D image analysis. Our method considers a Video to be a 1D sequence of clips, each one associated with its own semantics. The nature of these semantics – natural language captions or other labels – depends on the task at hand. A Test Video is processed by forming correspondences between its clips and the clips of reference Videos with known semantics, following which, reference semantics can be transferred to the Test Video. We describe two matching methods, both designed to ensure that (a) reference clips appear similar to Test clips and (b), taken together, the semantics of the selected reference clips is consistent and maintains temporal coherence. We use our method for Video captioning on the LSMDC’16 benchmark, Video summarization on the SumMe and TV-Sum benchmarks, Temporal Action Detection on the Thumos2014 benchmark, and sound prediction on the GreaTest Hits benchmark. Our method not only surpasses the state of the art, in four out of five benchmarks, but importantly, it is the only single method we know of that was successfully applied to such a diverse range of tasks.
Jing Zhongliang - One of the best experts on this subject based on the ideXlab platform.
-
Video-based Face Recognition Using Laplacianfaces and Hidden Markov Models
Computer Engineering, 2007Co-Authors: Jing ZhongliangAbstract:A method on Video-based face recognition using Laplacianfaces and Hidden Markov Models(HMM) is proposed.During the training process,all the training images in each subject are projected into the obtained Laplacianspace and corresponding feature vectors,which will be used as observation vectors in the HMM training are generated.The statistics of training Video sequences of each subject,and the temporal dynamics are learned by an HMM.During the recognition process,the temporal characteristics of Test Video sequence are analyzed over time by the HMM,and the highest score among the likelihood scores provided by HMM estimates the identity of the Test Video sequence.Experimental results show that the proposed method can get satisfied performance in Video-based face recognition.
Tsuhan Cheng - One of the best experts on this subject based on the ideXlab platform.
-
Video based face recognition using adaptive hidden markov models
Computer Vision and Pattern Recognition, 2003Co-Authors: Xiaoming Liu, Tsuhan ChengAbstract:While traditional face recognition is typically based on still images, face recognition from Video sequences has become popular. In this paper, we propose to use adaptive hidden Markov models (HMM) to perform Video-based face recognition. During the training process, the statistics of training Video sequences of each subject, and the temporal dynamics, are learned by an HMM. During the recognition process, the temporal characteristics of the Test Video sequence are analyzed over time by the HMM corresponding to each subject. The likelihood scores provided by the HMMs are compared, and the highest score provides the identity of the Test Video sequence. Furthermore, with unsupervised learning, each HMM is adapted with the Test Video sequence, which results in better modeling over time. Based on extensive experiments with various databases, we show that the proposed algorithm results in better performance than using majority voting of image-based recognition results.
-
CVPR (1) - Video-based face recognition using adaptive hidden Markov models
2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2003. Proceedings., 1Co-Authors: Xiaoming Liu, Tsuhan ChengAbstract:While traditional face recognition is typically based on still images, face recognition from Video sequences has become popular. In this paper, we propose to use adaptive hidden Markov models (HMM) to perform Video-based face recognition. During the training process, the statistics of training Video sequences of each subject, and the temporal dynamics, are learned by an HMM. During the recognition process, the temporal characteristics of the Test Video sequence are analyzed over time by the HMM corresponding to each subject. The likelihood scores provided by the HMMs are compared, and the highest score provides the identity of the Test Video sequence. Furthermore, with unsupervised learning, each HMM is adapted with the Test Video sequence, which results in better modeling over time. Based on extensive experiments with various databases, we show that the proposed algorithm results in better performance than using majority voting of image-based recognition results.
Dotan Kaufman - One of the best experts on this subject based on the ideXlab platform.
-
Temporal Tessellation: A Unified Approach for Video Analysis
International Conference on Computer Vision (ICCV), 2017Co-Authors: Dotan Kaufman, Gil Levi, Tal Hassner, Lior WolfAbstract:We present a general approach to Video understanding, inspired by semantic transfer techniques that have been successfully used for 2D image analysis. Our method considers a Video to be a 1D sequence of clips, each one associated with its own semantics. The nature of these semantics -- natural language captions or other labels -- depends on the task at hand. A Test Video is processed by forming correspondences between its clips and the clips of reference Videos with known semantics, following which, reference semantics can be transferred to the Test Video. We describe two matching methods, both designed to ensure that (a) reference clips appear similar to Test clips and (b), taken together, the semantics of the selected reference clips is consistent and maintains temporal coherence. We use our method for Video captioning on the LSMDC'16 benchmark, Video summarization on the SumMe and TVSum benchmarks, Temporal Action Detection on the Thumos2014 benchmark, and sound prediction on the GreaTest Hits benchmark. Our method not only surpasses the state of the art, in four out of five benchmarks, but importantly, it is the only single method we know of that was successfully applied to such a diverse range of tasks.
-
ICCV - Temporal Tessellation: A Unified Approach for Video Analysis
2017 IEEE International Conference on Computer Vision (ICCV), 2017Co-Authors: Dotan Kaufman, Gil Levi, Tal Hassner, Lior WolfAbstract:We present a general approach to Video understanding, inspired by semantic transfer techniques that have been successfully used for 2D image analysis. Our method considers a Video to be a 1D sequence of clips, each one associated with its own semantics. The nature of these semantics – natural language captions or other labels – depends on the task at hand. A Test Video is processed by forming correspondences between its clips and the clips of reference Videos with known semantics, following which, reference semantics can be transferred to the Test Video. We describe two matching methods, both designed to ensure that (a) reference clips appear similar to Test clips and (b), taken together, the semantics of the selected reference clips is consistent and maintains temporal coherence. We use our method for Video captioning on the LSMDC’16 benchmark, Video summarization on the SumMe and TV-Sum benchmarks, Temporal Action Detection on the Thumos2014 benchmark, and sound prediction on the GreaTest Hits benchmark. Our method not only surpasses the state of the art, in four out of five benchmarks, but importantly, it is the only single method we know of that was successfully applied to such a diverse range of tasks.
Gil Levi - One of the best experts on this subject based on the ideXlab platform.
-
Temporal Tessellation: A Unified Approach for Video Analysis
International Conference on Computer Vision (ICCV), 2017Co-Authors: Dotan Kaufman, Gil Levi, Tal Hassner, Lior WolfAbstract:We present a general approach to Video understanding, inspired by semantic transfer techniques that have been successfully used for 2D image analysis. Our method considers a Video to be a 1D sequence of clips, each one associated with its own semantics. The nature of these semantics -- natural language captions or other labels -- depends on the task at hand. A Test Video is processed by forming correspondences between its clips and the clips of reference Videos with known semantics, following which, reference semantics can be transferred to the Test Video. We describe two matching methods, both designed to ensure that (a) reference clips appear similar to Test clips and (b), taken together, the semantics of the selected reference clips is consistent and maintains temporal coherence. We use our method for Video captioning on the LSMDC'16 benchmark, Video summarization on the SumMe and TVSum benchmarks, Temporal Action Detection on the Thumos2014 benchmark, and sound prediction on the GreaTest Hits benchmark. Our method not only surpasses the state of the art, in four out of five benchmarks, but importantly, it is the only single method we know of that was successfully applied to such a diverse range of tasks.
-
ICCV - Temporal Tessellation: A Unified Approach for Video Analysis
2017 IEEE International Conference on Computer Vision (ICCV), 2017Co-Authors: Dotan Kaufman, Gil Levi, Tal Hassner, Lior WolfAbstract:We present a general approach to Video understanding, inspired by semantic transfer techniques that have been successfully used for 2D image analysis. Our method considers a Video to be a 1D sequence of clips, each one associated with its own semantics. The nature of these semantics – natural language captions or other labels – depends on the task at hand. A Test Video is processed by forming correspondences between its clips and the clips of reference Videos with known semantics, following which, reference semantics can be transferred to the Test Video. We describe two matching methods, both designed to ensure that (a) reference clips appear similar to Test clips and (b), taken together, the semantics of the selected reference clips is consistent and maintains temporal coherence. We use our method for Video captioning on the LSMDC’16 benchmark, Video summarization on the SumMe and TV-Sum benchmarks, Temporal Action Detection on the Thumos2014 benchmark, and sound prediction on the GreaTest Hits benchmark. Our method not only surpasses the state of the art, in four out of five benchmarks, but importantly, it is the only single method we know of that was successfully applied to such a diverse range of tasks.
