Video-based event recognition: activity representation and probabilistic recognition methods

By Somboon Hongeng, Ramkant Nevatia, Francois Bremond. Computer Vision and Image Understanding, 2004

342 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/2f198c8a75d5086bec32aece9fddb40793a11224

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. Andrew Zisserman
2. Michael S. Ryoo
3. Kristen Grauman
4. Ramalingam Chellappa
5. Li Fei-Fei
6. Deva Ramanan
7. Jake K. Aggarwal
8. Luc Van Gool

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Ming-Hsuan Yang
3. Dacheng Tao
4. Li Fei-Fei
5. Andrew Zisserman
6. Trevor Darrell
7. Jitendra Malik
8. Xiaogang Wang

In Human-Computer Interaction

1. Pavan K. Turaga
2. Ramalingam Chellappa
3. Michael S. Ryoo
4. Jake K. Aggarwal
5. Venkatramanan Siva Subrahmanian
6. Octavian Udrea
7. Fernando De la Torre
8. Cristian Sminchisescu

Citations in the corpus

• Understanding Video Events: A Survey of Methods for Automatic Interpretation of Semantic Occurrences in Video (2009, methodology): “[61] model the semantic hierarchy using BN layers.”
• Machine Recognition of Human Activities: A Survey (2008, background): “[123] extended this representation by considering an activity to be composed of several action threads.”
• CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning (2019, background): “Object tracking: Detecting and tracking objects has typically been used as an initial representation for long-term video and activity understanding (Shet et al., 2005; Hongeng et al., 2004; Lavee et al., 2009).”
• Spatio-temporal relationship match: Video structure comparison for recognition of complex human activities (2009, methodology): “built upon the tracking of persons and/or their body parts have also been developed [4, 11].”
• Conditional models for contextual human motion recognition (2006, background): “Human activity and behavior recognition, on the other hand, is challenging because human motion lacks a clear categorical structure: the motion can be often classified into several categories simultaneously, because some activities have a natural compositional (or concurrent) structure in terms of…”
• View-invariant motion trajectory-based activity classification and recognition (2006, background): “[19] have addressed the issue of activity recognition in single or multiple actor situations which exhibit some specific patterns of whole body motion.”
• Deliberation for autonomous robots: A survey (2017, background): “, in applications (column (iii) in Table 1) such as smart human–support environments [167], robot programming by demonstration [9] or video surveillance [103, 82].”
• Activity Recognition on Streaming Sensor Data (2012, methodology): “Researchers have also used data from video cameras monitoring and recognizing different activities [24][25].”
• Sequential Max-Margin Event Detectors (2014, background): “[9,19] modeled the temporal dynamics of activities for classification.”
• Searching Video for Complex Activities with Finite State Models (2007, background): “demonstrate recognition of multiperson activities from video of people at coarse scales (few kinematic details are available); activities include conversing and blocking [17].”