Proposal Distillation of Multi-Modal Feature Aggregation Network for Video Object Detection.
Zhenyu QiuQiang QiYang LuYan YanHanzi WangPublished in: ICASSP (2024)
Keyphrases
- multi modal
- object detection
- semantic concepts
- video search
- video content
- video sequences
- multi modality
- audio visual
- video streams
- feature vectors
- video data
- face detection
- cross modal
- wireless sensor networks
- image annotation
- video analysis
- multimedia
- multiple modalities
- single modality
- uni modal
- low level
- object categories
- video clips
- high dimensional
- object recognition