Journal
IEEE SIGNAL PROCESSING LETTERS
Volume 28, Issue -, Pages 1155-1159Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LSP.2021.3087079
Keywords
Semantics; Light rail systems; Measurement; Task analysis; Training; Message passing; Germanium; Deep learning; person re-identification; trans- former network; attention mechanism
Categories
Funding
- National Natural Science Foundation of China [61772513]
- Beijing Natural Science Foundation [19L2040]
Ask authors/readers for more resources
This method introduces the Self-guided Body Part Alignment technique, which avoids high dependence on external cues and performs well in occluded and holistic person re-identification tasks.
Person re-identification in the wild is often challenged by occlusion. Existing methods mainly rely on learned external cues like pose or parsing to ease occlusion distraction. This knowledge highly related to body semantics may introduce alignment effects, leading to additional requirements for dedicated training data and inference computation. We propose the Self-guided Body Part Alignment method that learns cue-free semantic-aligned local prediction for feature representations to avoid high-cost dependence on external cues. First, scale-wise global spatial attention is utilized to determine essential body parts automatically. A relation transformer network is then employed to predict semantic-aligned local parts, guided with anchored global information by constraint loss. Similarity metrics for all parts are merged with threshold conditions to filter invisible body parts comprehensively. Experimental results on occluded and holistic person reID benchmarks show the proposed method outperforms other cue-relied and cue-free methods. As far as we know, this is the first method that applies transformer networks on local predictions for occluded reID tasks.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available