Unsupervised Activity Perception by Hierarchical Bayesian Models

By Xiaogang Wang, Xiaoxu Ma, W. Grimson. 2007 IEEE Conference on Computer Vision and Pattern Recognition, 2007

343 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/1d3394c4f55380b47d979715916d5c447b94ee67

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Kristen Grauman
2. Xiaogang Wang
3. Mubarak Shah
4. Li Fei-Fei
5. Eric P. Xing
6. Kris M. Kitani
7. Jiaya Jia
8. Trevor Darrell

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Kristen Grauman
3. Ming-Hsuan Yang
4. Xiaogang Wang
5. Li Fei-Fei
6. Dacheng Tao
7. Yi Yang
8. Jitendra Malik

Citations in the corpus

• Observe locally, infer globally: A space-time MRF for detecting abnormal activities with incremental updates (2009, methodology): “The above methods [19, 18, 16, 11, 8] can be considered “global”, in the sense that they typically attempt to find the abnormal global activity patterns in a video clip in which several local activities can co-occur.”
• Fast unsupervised ego-action learning for first-person sports videos (2011, methodology): “The use of hierarchical mixture models have been shown useful modeling hierarchical grouping in such tasks as surveillance videos [16], documents analysis [14] and object categorization [8].”
• Abnormal Event Detection at 150 FPS in MATLAB (2013, methodology): “Graph model normal event representations were proposed in [21, 11, 10, 3, 19, 15, 6, 2], which utilize co-occurrence patterns.”
• Online detection of unusual events in videos via dynamic sparse coding (2011, background): “In this paper, we define unusual events as those incidences that occur very rarely in the entire video sequence [1, 7, 22, 3, 21, 14].”
• Trajectory Learning for Activity Understanding: Unsupervised, Multilevel, and Long-Term Adaptive Approach (2011, background): “[20], [21], [22] have developed hierarchical Bayesian models to group co-occurring motions into actions and activities, jointly and without supervision.”
• Multi-source Multi-scale Counting in Extremely Dense Crowd Images (2013, background): “Computation of such patterns of motion were also proposed in [22, 23, 12], but not with explicit application to the problem of crowd counting.”
• Intelligent multi-camera video surveillance: A review (2013, methodology): “Histogram of Oriented Gradients (HOG) (Dalal and Triggs, 2005; Wang et al., 2007; Schwartz and Davis, 2009) characterizes local shapes by capturing edges and gradient structures.”
• Spatial Latent Dirichlet Allocation (2007, methodology): “In visual surveillance, LDA was used to model atomic activities and interactions in a crowded scene [7].”
• Discovering Motion Primitives for Unsupervised Grouping and One-Shot Learning of Human Actions, Gestures, and Expressions (2013, positive): “The idea for the proposed representation is inspired by several recent works in traffic patterns discovery and representation [45], [20], [34].”