Total views : 151
A Comprehensive Study of Group Activity Recognition Methods in Video
Objectives: To provide comprehensive review of different group activity recognition methods, categorize them and provide path to new researcher in this domain. Methods/Statistical Analysis: Different methods of group activity recognition categorized and analyzed according to hand-crafted and learned feature descriptors. Pros and cons of each method are presented. Methods are analyzed in detailed by finding its local level features to global level feature descriptors used along with performance on benchmark dataset. Findings: Different models of group activity recognition are characterized as per the capabilities of the defined model considering individual pose of person, atomic activity of person, person-person interaction, person-group interaction, group-group interaction, uses of temporal information, and recognition of group activity frame wise or video wise. This comprehensive review provides brief information about group activity recognition methods and can be used as brief literature review to the researcher seeking the facts and findings in the field of computer vision in group activity recognition. Applications/Improvements: This reviews help in different applications of human activity analysis, mainly in group activity recognition and the models described here can be used in different applications such running or walking on pathways, waiting at public places, queuing in line in group and many more group activity applications for further enhancement.
Context Model, Convolution Neural Network, Group Activity Recognition, Group Descriptor, Interaction Model
- Tran KN, Gala A, Kakadiaris IA, Shah SK. Activity analysis in crowded environments using social cues for group discovery and human interaction modeling. Pattern Recognition Letters. 2014;44:49-57. Crossref
- Aggarwal JK, Ryoo MS. Human activity analysis. ACM Computing Surveys. 2011;43(3):1-43. Crossref
- Kaneko T, Shimosaka M, Odashima S, Fukui R, Sato T. A fully connected model for consistent collective activity recognition in videos. Pattern Recognition Letters. 2014;43:109-18. Crossref
- Wongun C, Shahid K, Savarese S. What are they doing? : Collective activity classification using spatio-temporal relationship among people. International Conference on Computer Vision Workshops, ICCV Workshops; 2009/09: IEEE; 2009. Crossref
- Choi W, Savarese S. A Unified Framework for Multi-target Tracking and Collective Activity Recognition. Computer Vision ECCV 2012: Springer Berlin Heidelberg; 2012;21530. Crossref
- Amer MR, Xie D, Zhao M, Todorovic S, Zhu S-C. CostSensitive Top-Down/Bottom-Up Inference for Multiscale Activity Recognition. Computer Vision ECCV 2012: Springer Berlin Heidelberg; 2012;187-200. Crossref
- Ibrahim MS, Muralidharan S, Deng Z, Vahdat A, Mori G. A Hierarchical Deep Temporal Model for Group Activity Recognition. Conference on Computer Vision and Pattern Recognition; 2016/06: IEEE; 2016. Crossref
- Dalal N, Triggs B. Histograms of Oriented Gradients for Human Detection. IEEE Computer Society Conference on Computer Vision and Pattern Recognition: IEEE; 2005. Crossref
- Felzenszwalb P, McAllester D, Ramanan D. A discriminatively trained, multiscale, deformable part model. Conference on Computer Vision and Pattern Recognition; 2008/06: IEEE; 2008. Crossref
- Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shape contexts. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2002;24(4):509-22. Crossref
- Lan T, Wang Y, Mori G, Robinovitch SN. Retrieving Actions in Group Contexts. Trends and Topics in Computer Vision: Springer Berlin Heidelberg; 2012;181-94. Crossref
- Kaneko T, Shimosaka M, Odashima S, Fukui R, Sato T. Viewpoint Invariant Collective Activity Recognition with Relative Action Context. Computer Vision ECCV 2012 Workshops and Demonstrations: Springer Berlin Heidelberg; 2012;253-62. Crossref
- Kim Y-J, Cho N-G, Lee S-W. Group Activity Recognition with Group Interaction Zone. 2014 22nd International Conference on Pattern Recognition; 2014/08: IEEE; 2014. Crossref
- Lan T, Wang Y, Yang W, Mori G, editors. Beyond actions: Discriminative models for contextual group activities. Advances in neural information processing systems; 2010.
- Amer MR, Todorovic S. A chains model for localizing participants of group activities in videos. International Conference on Computer Vision; 2011/11: IEEE; 2011. Crossref
- Noceti N, Odone F. A Spectral Graph Kernel and Its Application to Collective Activities Classification. 22nd International Conference on Pattern Recognition; 2014/08: IEEE; 2014. Crossref
- Noceti N, Odone F. Humans in groups: The importance of contextual information for understanding collective activities. Pattern Recognition. 2014;47(11):3535-51. Crossref
- Li R, Chellappa R, Zhou SK. Recognizing Interactive Group Activities Using Temporal Interaction Matrices and Their Riemannian Statistics. International Journal of Computer Vision. 2012;101(2):305-28. Crossref
- Kihwan K, Dongryeol L, Essa I. Detecting regions of interest in dynamic scenes with camera motions. IEEE Conference on Computer Vision and Pattern Recognition; 2012/06: IEEE; 2012. Crossref
- Blunsden S, Fisher R. The BEHAVE video dataset: ground truthed video for multi-person behavior classification. Annals of the BMVA. 2010;4(1-12):4.
- Zhou Z, Li K, He X, Li M, editors. A Generative Model for Recognizing Mixed Group Activities in Still Images. 25th International Joint Conference on Artificial Intelligence; 2016: AAAI Press.
- Kaneko T, Shimosaka M, Odashima S, Fukui R, Sato T, editors. Consistent collective activity recognition with fully connected CRFs. 21st International Conference on Pattern Recognition; 2012: IEEE.
- Sun D, Roth S, Black MJ. Secrets of optical flow estimation and their principles. IEEE Computer Society Conference on Computer Vision and Pattern Recognition; 2010/06: IEEE; 2010. Crossref
- Choi W, Savarese S. Understanding Collective Activitiesof People from Videos. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2014;36(6):1242-57. Crossref
- Tian L, Yang W, Weilong Y, Robinovitch SN, Mori G. Discriminative Latent Models for Recognizing Contextual Group Activities. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2012;34(8):1549-62. Crossref
- Laptev I, Marszalek M, Schmid C, Rozenfeld B. Learning realistic human actions from movies. IEEE Conference on Computer Vision and Pattern Recognition; 2008/06: IEEE; 2008. Crossref
- Amer MR, Todorovic S, Fern A, Zhu S-C. Monte Carlo Tree Search for Scheduling Activity Recognition. IEEE International Conference on Computer Vision; 2013/12: IEEE; 2013. Crossref
- Si Z, Pei M, Yao B, Zhu S-C. Unsupervised learning of event AND-OR grammar and semantics from video. International Conference on Computer Vision; 2011/11: IEEE; 2011. Crossref
- Pei M, Yunde J, Zhu S-C. Parsing video events with goal inference and intent prediction. International Conference on Computer Vision; 2011/11: IEEE; 2011. Crossref
- Tran KN, Yan X, Kakadiaris IA, Shah SK. A Group Contextual Model for Activity Recognition in Crowded Scenes. Proceedings of the 10th International Conference on Computer Vision Theory and Applications: SCITEPRESS Science and and Technology Publications; 2015. Crossref
- Nabi M, Del Bue A, Murino V. Temporal Poselets for Collective Activity Detection and Recognition. IEEE International Conference on Computer Vision Workshops; 2013/12: IEEE; 2013. Crossref
- Sun L, Ai H, Lao S. Activity Group Localization by Modeling the Relations among Participants. Computer Vision ECCV 2014: Springer International Publishing; 2014;741-55. Crossref
- Hajimirsadeghi H, Mori G. Learning Ensembles of Potential Functions for Structured Prediction with Latent Variables. IEEE International Conference on Computer Vision; 2015/12: IEEE; 2015. Crossref
- Hajimirsadeghi H, Wang Y, Vahdat A, Mori G. Visual recognition by counting instances: A multi-instance cardinality potential kernel. IEEE Conference on Computer Vision and Pattern Recognition; 2015/06: IEEE; 2015. Crossref
- Donahue J, Hendricks LA, Guadarrama S, Rohrbach M, Venugopalan S, Darrell T, et al. Long-term recurrent convolutional networks for visual recognition and description. IEEE Conference on Computer Vision and Pattern Recognition; 2015/06: IEEE; 2015. Crossref
- Soomro K, Zamir AR, Shah M. UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:12120402. 2012.
- Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, et al. Caffe. Proceedings of the ACM International Conference on Multimedia - MM ‘14: ACM Press; 2014. Crossref
- Zeiler MD, Fergus R. Visualizing and Understanding Convolutional Networks. Computer Vision ECCV 2014: Springer International Publishing; 2014;818-33. Crossref
- Xiaobin C, Wei-Shi Z, Jianguo Z. Learning Person-Person Interaction in Collective Activity Recognition. IEEE Transactions on Image Processing. 2015;24(6):1905-18. Crossref
- Deng Z, Zhai M, Chen L, Liu Y, Muralidharan S, Roshtkhari MJ, et al. Deep Structured Models For Group Activity Recognition. Procedings of the British Machine Vision Conference: British Machine Vision Association; 2015. Crossref
- Krizhevsky A, Sutskever I, Hinton GE, editors. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems; 2012.
- Deng Z, Vahdat A, Hu H, Mori G. Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition. IEEE Conference on Computer Vision and Pattern Recognition; 2016/06: IEEE; 2016. Crossref
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution 3.0 License.