AI models
Trajectory-pooled conv nets
Parameters
9.1M
Published
May 19, 2015
Trajectory-pooled conv nets is an AI model developed by Chinese University of Hong Kong (CUHK) and Chinese Academy of Sciences (Hong Kong and China), first published in May 2015. It works in the video domain, on tasks such as action recognition.
Epoch AI has no training-compute estimate for this model. The model has 9,106,245 parameters.
The reference paper has 3,786 citations.
Full record
- Organization
- Chinese University of Hong Kong (CUHK), Chinese Academy of Sciences
- Country of organization
- Hong Kong, China
- Domain
- Video
- Task
- Action recognition
- Parameters
- 9,106,245
- Numerical format
- FP32
- Citations
- 3,786
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models