Occluded Person Re-Identification
23 papers with code • 0 benchmarks • 0 datasets
Occluded Person Re-Identification (ReID) is a person retrieval task closely related to Person Re-Identification that involves matching occluded individuals based on their appearance.
Benchmarks
These leaderboards are used to track progress in Occluded Person Re-Identification
Most implemented papers
Body Part-Based Representation Learning for Occluded Person Re-Identification
vlsomers/bpbreid
•
•
Firstly, individual body part appearance is not as discriminative as global appearance (two distinct IDs might have the same local appearance), this means standard ReID training objectives using identity labels are not adapted to local feature learning.
High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification
wangguanan/HOReID
•
•
CVPR 2020
When aligning two groups of local features from two images, we view it as a graph matching problem and propose a cross-graph embedded-alignment (CGEA) layer to jointly learn and embed topology information to local features, and straightly predict similarity score.
Dynamic Prototype Mask for Occluded Person Re-Identification
stone96123/dpm
•
•
Although person re-identification has achieved an impressive improvement in recent years, the common occlusion case caused by different obstacles is still an unsettled issue in real application scenarios.
Keypoint Promptable Re-Identification
vlsomers/bpbreid
•
•
Inspired by recent work on prompting in vision, we introduce Keypoint Promptable ReID (KPR), a novel formulation of the ReID problem that explicitly complements the input bounding box with a set of semantic keypoints indicating the intended target.
Pose-Guided Feature Alignment for Occluded Person Re-Identification
lightas/ICCV19_Pose_Guided_Occluded_Person_ReID
•
•
ICCV 2019
Our method largely outperforms existing person re-id methods on three occlusion datasets, while remains top performance on two holistic datasets.
Pose-guided Visible Part Matching for Occluded Person ReID
Occluded person re-identification is a challenging task as the appearance varies substantially with various obstacles, especially in the crowd scenario.
MHSA-Net: Multi-Head Self-Attention Network for Occluded Person Re-Identification
This paper presents a novel person re-identification model, named Multi-Head Self-Attention Network (MHSA-Net), to prune unimportant information and capture key local information from person images.
Holistic Guidance for Occluded Person Re-Identification
madhukiranets/holisitcguidanceoccreid2
•
•
Hence, our proposed student-teacher framework is trained to address the occlusion problem by matching the distributions of between- and within-class distances (DCDs) of occluded samples with that of holistic (non-occluded) samples, thereby using the latter as a soft labeled reference to learn well separated DCDs.
Feature Completion for Occluded Person Re-Identification
blue-blue272/OccludedReID-RFCnet
•
•
Our method significantly outperforms existing methods on the occlusion datasets, while remains top even superior performance on holistic datasets.
Pose-guided Inter- and Intra-part Relational Transformer for Occluded Person Re-Identification
iCVTEAM/Pirt
•
•
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.
