Multi-modal visual tracking based on textual generation.
Jiahao WangFang LiuLicheng JiaoHao WangShuo LiLingling LiPuhua ChenXu LiuPublished in: Inf. Fusion (2024)
Keyphrases
- uni modal
- visual tracking
- multi modal
- mean shift
- particle filter
- particle filtering
- hand tracking
- appearance model
- object tracking
- video sequences
- real time tracking
- data association
- feature space
- cross modal
- partial occlusion
- image annotation
- articulated structures
- humanoid robot
- high dimensional
- computer vision
- multi modality
- kalman filter
- image retrieval