Video Action Segmentation via Contextually Refined Temporal Keypoints.
Borui JiangYang JinZhentao TanYadong MuPublished in: ICCV (2023)
Keyphrases
- keypoints
- temporal segmentation
- multiscale
- temporal coherence
- spatial and temporal
- video sequences
- space time
- human actions
- temporal information
- temporal consistency
- image matching
- video data
- spatio temporal
- scale invariant
- keypoint detection
- image features
- segmentation algorithm
- sift features
- image segmentation
- object recognition
- medical images
- atomic actions
- sift descriptors
- scale invariant feature transform
- video frames
- feature detection
- visual words
- image sequences
- shape representation
- shape prior
- dynamic textures
- feature vectors
- scale space