Action and Gesture Temporal Spotting with Super Vector Representation

详细信息    查看全文

• 作者：Xiaojiang Peng (16) (18)
  Limin Wang (17) (18)
  Zhuowei Cai (18)
  Yu Qiao (18)
  
  16. Southwest Jiaotong University ; Chengdu ; China
  18. Shenzhen Key Lab of CVPR ; Shenzhen Institutes of Advanced Technology ; CAS ; Shenzhen ; China
  17. Department of Information Engineering ; The Chinese University of Hong Kong ; Hong Kong ; China
  
• 关键词：Action recognition ; Gesture recognition ; Temporal spotting ; Super vector
• 刊名：Lecture Notes in Computer Science
• 出版年：2015
• 出版时间：2015
• 年：2015
• 卷：8925
• 期：1
• 页码：518-527
• 全文大小：1,103 KB
• 参考文献：1. Escalera, S Chalearn looking at people challenge 2014: dataset and results. In: Bronstein, M, Agapito, L, Rother, C eds. (2015) Computer Vision - ECCV 2014 Workshops. Springer, Heidelberg, pp. 459-473 CrossRef
  2. Aggarwal, JK, Ryoo, MS (2011) Human activity analysis: A review. ACM Comput. Surv. 43: pp. 16 CrossRef
  3. Mitra, S, Acharya, T (2007) Gesture recognition: A survey. IEEE Transactions on Systems, Man, and Cybernetics, Part C 37: pp. 311-324 CrossRef
  4. Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: ICCV, pp. 2556鈥?563 (2011)
  5. Soomro, K., Zamir, A.R., Shah, M.: UCF101: A dataset of 101 human actions classes from videos in the wild. CoRR abs/1212.0402 (2012)
  6. Sanchez, D., Bautista, M., Escalera, S.: Hupab 8k+: Dataset and ecoc-graphcut based segmentation of human limbs. Neurocomputing (2014)
  7. Escalera, S., Gonz脿lez, J., Bar贸, X., Reyes, M., Lopes, O., Guyon, I., Athitsos, V., Escalante, H.J.: Multi-modal gesture recognition challenge 2013: dataset and results. In: ICMI, pp. 445鈥?52 (2013)
  8. Wang, H, Kl盲ser, A, Schmid, C, Liu, CL (2013) Dense trajectories and motion boundary descriptors for action recognition. International Journal of Computer Vision 103: pp. 60-79 CrossRef
  9. Perronnin, F, S谩nchez, J, Mensink, T Improving the fisher kernel for large-scale image classification. In: Daniilidis, K, Maragos, P, Paragios, N eds. (2010) Computer Vision 鈥?ECCV 2010. Springer, Heidelberg, pp. 143-156 CrossRef
  10. Sivic, J., Zisserman, A.: Video google: a text retrieval approach to object matching in videos. In: ICCV, pp. 1470鈥?477 (2003)
  11. Wang, X, Wang, LM, Qiao, Y A comparative study of encoding, pooling and normalization methods for action recognition. In: Lee, KM, Matsushita, Y, Rehg, JM, Hu, Z eds. (2013) Computer Vision 鈥?ACCV 2012. Springer, Heidelberg, pp. 572-585 CrossRef
  12. Peng, X., Wang, L., Wang, X., Qiao, Y.: Bag of visual words and fusion methods for action recognition: Comprehensive study and good practice. CoRR abs/1405.4506 (2014)
  13. Vedaldi, A., Fulkerson, B.: VLFeat: An open and portable library of computer vision algorithms (2008). http://www.vlfeat.org/
  14. Jaakkola, T., Haussler, D.: Exploiting generative models in discriminative classifiers. In: NIPS, pp. 487鈥?93 (1998)
  15. Chang, CC, Lin, CJ (2011) LIBSVM: A library for support vector machines. ACM TIST 2: pp. 27
  16. Yong, P, Bingbing, N, Indriyati, A Mixture of heterogeneous attribute analyzers for human action detection. In: Bronstein, M, Agapito, L, Rother, C eds. (2015) Computer Vision - ECCV 2014 Workshops. Springer, Heidelberg, pp. 528-540 CrossRef
  17. Shu, Z, Yun, K, Samaras, D Action detection with improved dense trajectories and sliding window. In: Bronstein, M, Agapito, L, Rother, C eds. (2015) Computer Vision - ECCV 2014 Workshops. Springer, Heidelberg, pp. 541-551 CrossRef
  18. Neverova, N, Wolf, C, Taylor, GW, Nebout, F (2015) Multi-scale deep learning for gesture detection and localization. Computer Vision - ECCV 2014 Workshops. Springer, Heidelberg, pp. 474-490 CrossRef
  19. Monnier, C, German, S, Ost, A A multi-scale boosted detector for efficient and robust gesture recognition. In: Bronstein, M, Agapito, L, Rother, C eds. (2015) Computer Vision - ECCV 2014 Workshops. Springer, Heidelberg, pp. 491-502 CrossRef
  20. Chang, JY Nonparametric gesture labeling from multi-modal data. In: Bronstein, M, Agapito, L, Rother, C eds. (2015) Computer Vision - ECCV 2014 Workshops. Springer, Heidelberg, pp. 503-517 CrossRef
  
• 作者单位：Computer Vision - ECCV 2014 Workshops
• 丛书名：978-3-319-16177-8
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349

文摘

This paper focuses on describing our method designed for both track 2 and track 3 at Looking at People (LAP) challenging [1]. We propose an action and gesture spotting system, which is mainly composed of three steps: (i) temporal segmentation, (ii) clip classification, and (iii) post processing. For track 2, we resort to a simple sliding window method to divide each video sequence into clips, while for track 3, we design a segmentation method based on the motion analysis of human hands. Then, for each clip, we choose a kind of super vector representation with dense features. Based on this representation, we train a linear SVM to conduct action and gesture recognition. Finally, we use some post processing techniques to void the detection of false positives. We demonstrate the effectiveness of our proposed method by participating the contests of both track 2 and track 3. We obtain the best performance on track 2 and rank \(4^{th}\) on track 3, which indicates that the designed system is effective for action and gesture recognition.