Context Enhanced Transformer for Single Image Object Detection in Video Data.
Seungjun AnSeonghoon ParkGyeongnyeon KimJeongyeol BaekByeongwon LeeSeungryong KimPublished in: AAAI (2024)
Keyphrases
- single image
- video data
- object detection
- shape recovery
- video streams
- video sequences
- video analysis
- video content
- multimedia
- multiple images
- d scene
- video frames
- super resolution
- video retrieval
- light source
- video camera
- computer vision
- temporal structure
- scene understanding
- background subtraction
- object categories
- key frames
- lighting conditions
- multiscale
- high quality
- intrinsic image decomposition