ABSTRACT
Images with wider angles usually capture more persons in wider scenes, and recognizing individuals' activities in these images based on existing contextual cues usually meet difficulties. We instead construct a novel group-based cue to utilize the context carried by suitable surrounding persons. We propose a global-local cue integration model (GLCIM) to find a suitable group of local cues extracted from individuals and form a corresponding global cue. A fusion restricted Boltzmann machine, a focal subspace measurement and a cue integration algorithm based on entropy are proposed to enable the GLCIM to integrate most of the relevant local cues and least of the irrelevant ones into the group. Our experiments demonstrate how integrating group-based cues improves the activity recognition accuracies in detail and show that all of the key parts of GLCIM make positive contributions to the increases of the accuracies.
- M. R. Amer, D. Xie, M. Zhao, S. Todorovic, and S.-C. Zhu. Cost-sensitive top-down/bottom-up inference for multiscale activity recognition. In ECCV, 187--200, 2012. Google ScholarDigital Library
- Z. Cheng, L. Qin, Q. Huang, S. Yan, and Q. Tian. Recognizing human group action by layered model with multiple cues. Neurocomputing, 136:124--135, 2014.Google ScholarCross Ref
- W. Choi, Y.-W. Chao, C. Pantofaru, and S. Savarese. Discovering groups of people in images. In ECCV, 417--433, 2014.Google ScholarCross Ref
- P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan. Object detection with discriminatively trained part-based models. T-PAMI, 32(9):1627--1645, 2010. Google ScholarDigital Library
- G. Guo and A. Lai. A survey on still image based human action recognition. Pattern Recognition, 2014.Google Scholar
- T. Lan, Y. Wang, W. Yang, S. N. Robinovitch, and G. Mori. Discriminative latent models for recognizing contextual group activities. T-PAMI, 34(8):1549--1562, 2012. Google ScholarDigital Library
- L.-J. Li and L. Fei-Fei. What, where and who? classifying events by scene and object recognition. In ICCV, 1--8, 2007.Google ScholarCross Ref
- T. B. Moeslund, A. Hilton, and V. Krüger. A survey of advances in vision-based human motion capture and analysis. CVIU, 104(2):90--126, 2006. Google ScholarDigital Library
- A. Prest, C. Schmid, and V. Ferrari. Weakly supervised learning of interactions between humans and objects. T-PAMI, 34(3):601--614, 2012. Google ScholarDigital Library
- N. Shapovalova, W. Gong, M. Pedersoli, F. X. Roca, and J. Gonzàlez. On importance of interactions and context in human action recognition. In Pattern Recognition and Image Analysis, pages 58--66. 2011. Google ScholarDigital Library
- T.-H. Vu, C. Olsson, I. Laptev, A. Oliva, and J. Sivic. Predicting actions from static scenes. In ECCV, 421--436, 2014.Google ScholarCross Ref
- B. Yao and L. Fei-Fei. Recognizing human-object interactions in still images by modeling the mutual context of objects and human poses. T-PAMI, 34(9):1691--1703, 2012. Google ScholarDigital Library
- Z.-J. Zha, H. Zhang, M. Wang, H. Luan, and T.-S. Chua. Detecting group activities with multi-camera context. T-CSVT, 23(5):856--869, 2013. Google ScholarDigital Library
Index Terms
- Recognizing Human Activity in Still Images by Integrating Group-Based Contextual Cues
Recommendations
Quantifying the Contextual Separability of Visual Confusion
AIMS '13: Proceedings of the 2013 1st International Conference on Artificial Intelligence, Modelling and SimulationVisual information and contextual knowledge can both contribute to the overall performance of an object recognition system. However, little work has so far been done to quantify the extent to which context can compensate for visual error and confusion. ...
Promoting Social Connectedness through Human Activity-Based Ambient Displays
ITAP '16: Proceedings of the International Symposium on Interactive Technology and Ageing PopulationsExisting research in ambient assisted living (AAL) confirms the success of context aware applications in conveying feelings of connectedness and creating a sense of co-presence. Awareness of an elder's activities could trigger emotional responses and ...
Batch-based activity recognition from egocentric photo-streams revisited
Wearable cameras can gather large amounts of image data that provide rich visual information about the daily activities of the wearer. Motivated by the large number of health applications that could be enabled by the automatic recognition of daily ...
Comments