Multi-Object Tracking by Hierarchical Visual Representations
This addresses tracking challenges for computer vision applications, but it is incremental as it builds on existing appearance-based methods.
The paper tackles multi-object tracking by introducing a hierarchical visual representation paradigm that uses compositional regions and background context, achieving state-of-the-art accuracy and time efficiency on benchmarks.
We propose a new visual hierarchical representation paradigm for multi-object tracking. It is more effective to discriminate between objects by attending to objects' compositional visual regions and contrasting with the background contextual information instead of sticking to only the semantic visual cue such as bounding boxes. This compositional-semantic-contextual hierarchy is flexible to be integrated in different appearance-based multi-object tracking methods. We also propose an attention-based visual feature module to fuse the hierarchical visual representations. The proposed method achieves state-of-the-art accuracy and time efficiency among query-based methods on multiple multi-object tracking benchmarks.