HecVL: Hierarchical Video-Language Pretraining for Zero-shot Surgical Phase Recognition.
Kun YuanVinkle SrivastavNassir NavabNicolas PadoyPublished in: CoRR (2024)
Keyphrases
- video sequences
- object recognition
- recognition rate
- language learning
- video content
- pattern recognition
- programming language
- video data
- automatic recognition
- recognition accuracy
- video streams
- human activities
- static images
- video frames
- recognition process
- video surveillance
- video analysis
- computer vision
- recognition algorithm
- event recognition
- event detection
- activity recognition
- action recognition
- natural language
- real time
- multimedia data
- object categories
- hierarchical structure
- hand gestures
- medical images
- image registration
- feature extraction
- video images
- indian languages