Clothes-Changing Person Re-Identification with Feasibility-Aware Intermediary Matching
Not on the map. Why?
Abstract (arXiv)
Current clothes-changing person re-identification (re-id) approaches usually perform retrieval based on clothes-irrelevant features, while neglecting the potential of clothes-relevant features. However, we observe that relying solely on clothes-irrelevant features for clothes-changing re-id is limited, since they often lack adequate identity information and suffer from large intra-class variations. On the contrary, clothes-relevant features can be used to discover same-clothes intermediaries that possess informative identity clues. Based on this observation, we propose a Feasibility-Aware Intermediary Matching (FAIM) framework to additionally utilize clothes-relevant features for retrieval. Firstly, an Intermediary Matching (IM) module is designed to perform an intermediary-assisted matching process. This process involves using clothes-relevant features to find informative intermediates, and then using clothes-irrelevant features of these intermediates to complete the matching. Secondly, in order to reduce the negative effect of low-quality intermediaries, an Intermediary-Based Feasibility Weighting (IBFW) module is designed to evaluate the feasibility of intermediary matching process by assessing the quality of intermediaries. Extensive experiments demonstrate that our method outperforms state-of-the-art methods on several widely-used clothes-changing re-id benchmarks.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 38 of its 73 references that are in the map. First posted on arXiv 15 Apr 2024.
Builds on
38 of 73 references.
References · 38
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2017Neural Message Passing for Quantum Chemistrycited by 3,487
- 2017Random Erasing Data Augmentationcited by 1,239
- 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 903
- 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 786
- 2017Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)cited by 473
- 2019Omni-Scale Feature Learning for Person Re-Identificationcited by 295
- 2018Learning Discriminative Features with Multiple Granularities for Person Re-Identificationcited by 291
- 2017Re-ranking Person Re-identification with k-reciprocal Encodingcited by 262
- 2021Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformercited by 120
- 2019Implicit Semantic Data Augmentation for Deep Networkscited by 106
- 2022Clothes-Changing Person Re-identification with RGB Modality Onlycited by 98
26 more
- 2020Person Re-identification by Contour Sketch under Moderate Clothing Changecited by 91
- 2020Long-Term Cloth-Changing Person Re-identificationcited by 85
- 2019Interaction-and-Aggregation Network for Person Re-identificationcited by 80
- 2021Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularizationcited by 69
- 2020Appearance-Preserving 3D Convolution for Video-based Person Re-identificationcited by 63
- 2021Instance-level Image Retrieval using Reranking Transformerscited by 63
- 2018Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsingcited by 60
- 2020Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identificationcited by 50
- 2021BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identificationcited by 44
- 2020COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identificationcited by 35
- 2023Learning Clothing and Pose Invariant 3D Shape Representation for Long-Term Person Re-Identificationcited by 34
- 2020Uncertainty-Aware Multi-Shot Knowledge Distillation for Image-Based Object Re-Identificationcited by 32
- 2021Face.evoLVe: A High-Performance Face Recognition Librarycited by 26
- 2020Learning Longterm Representations for Person Re-Identification Using Radio Signalscited by 25
- 2020Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspectivecited by 24
- 2021Semantic-guided Pixel Sampling for Cloth-Changing Person Re-identificationcited by 22
- 2023Adaptive Sparse Pairwise Loss for Object Re-Identificationcited by 20
- 2022Asymmetric Cross-Scale Alignment for Text-Based Person Searchcited by 18
- 2023Semantic-aware Consistency Network for Cloth-changing Person Re-Identificationcited by 18
- 2019Temporal Knowledge Propagation for Image-to-Video Person Re-identificationcited by 17
- 2023MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReIDcited by 16
- 2022Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrievalcited by 12
- 2022Pseudo-Pair based Self-Similarity Learning for Unsupervised Person Re-identificationcited by 11
- 2020IAUnet: Global Context-Aware Feature Learning for Person Re-Identificationcited by 10
- 2022Learning Resolution-Adaptive Representations for Cross-Resolution Person Re-Identificationcited by 5
- 2022Identity-Sensitive Knowledge Propagation for Cloth-Changing Person Re-identificationcited by 5
Built on by
Citing papers per year: 2024: 1; 2025: 0; 2026: 1.
2 papers.