Pose-guided Inter- and Intra-part Relational Transformer for Occluded Person Re-Identification
release_4cpwmkkqkrccnbiy3dqiaoqbjm
by
Zhongxing Ma, Yifan Zhao, Jia Li
2021
Abstract
Person Re-Identification (Re-Id) in occlusion scenarios is a challenging
problem because a pedestrian can be partially occluded. The use of local
information for feature extraction and matching is still necessary. Therefore,
we propose a Pose-guided inter-and intra-part relational transformer (Pirt) for
occluded person Re-Id, which builds part-aware long-term correlations by
introducing transformers. In our framework, we firstly develop a pose-guided
feature extraction module with regional grouping and mask construction for
robust feature representations. The positions of a pedestrian in the image
under surveillance scenarios are relatively fixed, hence we propose an
intra-part and inter-part relational transformer. The intra-part module creates
local relations with mask-guided features, while the inter-part relationship
builds correlations with transformers, to develop cross relationships between
part nodes. With the collaborative learning inter- and intra-part
relationships, experiments reveal that our proposed Pirt model achieves a new
state of the art on the public occluded dataset, and further extensions on
standard non-occluded person Re-Id datasets also reveal our comparable
performances.
In text/plain
format
Archived Files and Locations
application/pdf 7.7 MB
file_3qo4by32t5dk7k6mkykpimfz6a
|
arxiv.org (repository) web.archive.org (webarchive) |
2109.03483v1
access all versions, variants, and formats of this works (eg, pre-prints)