In *Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on*, pages 1-8, June, 2008.

doi abstract bibtex

doi abstract bibtex

Given an input video sequence of one person conducting a sequence of continuous actions, we consider the problem of jointly segmenting and recognizing actions. We propose a discriminative approach to this problem under a semi-Markov model framework, where we are able to define a set of features over input-output space that captures the characteristics on boundary frames, action segments and neighboring action segments, respectively. In addition, we show that this method can also be used to recognize the person who performs in this video sequence. A Viterbi-like algorithm is devised to help efficiently solve the induced optimization problem. Experiments on a variety of datasets demonstrate the effectiveness of the proposed method.

@InProceedings{Shi2008, Title = {Discriminative human action segmentation and recognition using semi-Markov model}, Author = {Qinfeng Shi and Li Wang and Li Cheng and Smola, A.}, Booktitle = {Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on}, Year = {2008}, Month = {June}, Pages = {1-8}, Abstract = {Given an input video sequence of one person conducting a sequence of continuous actions, we consider the problem of jointly segmenting and recognizing actions. We propose a discriminative approach to this problem under a semi-Markov model framework, where we are able to define a set of features over input-output space that captures the characteristics on boundary frames, action segments and neighboring action segments, respectively. In addition, we show that this method can also be used to recognize the person who performs in this video sequence. A Viterbi-like algorithm is devised to help efficiently solve the induced optimization problem. Experiments on a variety of datasets demonstrate the effectiveness of the proposed method.}, Doi = {10.1109/CVPR.2008.4587557}, ISSN = {1063-6919}, Keywords = {Markov processes;image recognition;image segmentation;image sequences;maximum likelihood estimation;video signal processing;Viterbi-like algorithm;action segments;boundary frames;discriminative human action segmentation-recognition;optimization problem;semiMarkov model;video sequence;Character recognition;Hidden Markov models;Humans;Inference algorithms;Shape;Support vector machines;Surveillance;Tracking;Video sequences}, Timestamp = {2014.12.23} }

Downloads: 0