https://github.com/charliememory/PKU-Reid-Dataset
공식 코드Orientation Driven Bag of Appearances for Person Re-identification
Papers with Code 아카이브
Person Re-Identification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 13
- 평가표
- 41
- 보존된 평가 기록
- 533
Person Re-Identification is a computer vision task in which the goal is to match a person's identity across different cameras or locations in a video or image sequence. It involves detecting and tracking a person and then using features such as appearance, body shape, and clothing to match their identity in different frames. The goal is to associate the same person across multiple non-overlapping camera views in a robust and efficient manner.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/chen960/ca-jaccard
공식 코드CA-Jaccard: Camera-aware Jaccard Distance for Person Re-identification
https://github.com/chenbinghui1/MHN
공식 코드Mixed High-Order Attention Network for Person Re-Identification
https://github.com/chengy12/apnet
공식 코드https://github.com/chenhao2345/ABMT
공식 코드https://github.com/chenhao2345/GCL
공식 코드Joint Generative and Contrastive Learning for Unsupervised Person Re-identification
https://github.com/chenhao2345/ICE
공식 코드ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification
https://github.com/chenhao2345/gcl-extended
공식 코드Learning Invariance from Generated Variance for Unsupervised Person Re-identification
https://github.com/chenhao2345/ucr
공식 코드Unsupervised Lifelong Person Re-identification via Contrastive Rehearsal
https://github.com/chenlq123/MAE
공식 코드https://github.com/chequanghuy/Enhancing-Person-Re-Identification-via-UFFM-and-AMC
공식 코드https://github.com/cly234/lreid-krkc
공식 코드Lifelong Person Re-Identification via Knowledge Refreshing and Consolidation
https://github.com/codegallery24/cpcl
공식 코드https://github.com/crazydemo/Progressive-Multi-stage-Feature-Mix-for-Person-Re-Identification
공식 코드Progressive Multi-stage Feature Mix for Person Re-Identification
https://github.com/croitorualin/dlcr
공식 코드DLCR: A Generative Data Expansion Framework via Diffusion for Clothes-Changing Person Re-ID
https://github.com/cuixxx/profd
공식 코드ProFD: Prompt-Guided Feature Disentangling for Occluded Person Re-Identification
https://github.com/cvlab-yonsei/OIMNetPlus
공식 코드OIMNet++: Prototypical Normalization and Localization-aware Learning for Person Search
https://github.com/cvlab-yonsei/RRID
공식 코드https://github.com/cvlab-yonsei/STMN
공식 코드Video-based Person Re-identification with Spatial and Temporal Memory Networks
https://github.com/cvlab-yonsei/projects
공식 코드Learning Disentangled Representation for Robust Person Re-identification
https://github.com/d-li14/HBONet
공식 코드https://github.com/damo-cv/transreid
공식 코드https://github.com/danielshalam/bpa
공식 코드https://github.com/daodaofr/AlignPS
공식 코드https://github.com/daodaofr/caffe-re-id
공식 코드https://github.com/daodaofr/group_reid
공식 코드Learning Multi-Attention Context Graph for Group-Based Re-Identification
https://github.com/daodaofr/hypergraph_reid
공식 코드Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification
https://github.com/dcp15/isr_iccv2023_oral
공식 코드Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-identification
https://github.com/deanchan/keypointmessagepassing
공식 코드Keypoint Message Passing for Video-based Person Re-Identification
https://github.com/deepmind/deepmind-research/tree/master/byol
공식 코드Bootstrap your own latent: A new approach to self-supervised Learning
https://github.com/dengpanfu/luperson-nl
공식 코드Large-Scale Pre-training for Person Re-identification with Noisy Labels
https://github.com/deropty/LDS
공식 코드https://github.com/deropty/PiT
공식 코드Multi-direction and Multi-scale Pyramid in Transformer for Video-based Pedestrian Retrieval
https://github.com/deropty/uPMnet
공식 코드Exploiting Robust Unsupervised Video Person Re-identification
https://github.com/djidje/D-MMD
공식 코드Unsupervised Domain Adaptation in the Dissimilarity Space for Person Re-identification
https://github.com/duggalrahul/MICCAI17_EndoVis_RoboSeg
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.