https://github.com/SheldongChen/AMD.github.io
공식 코드Explainable Person Re-Identification with Attribute-guided Metric Distillation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Explainable Person Re-Identification with Attribute-guided Metric Distillation
TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification
Joint Detection and Identification Feature Learning for Person Search
IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID
Adversarial Metric Attack and Defense for Person Re-identification
Lifelong Person Re-Identification via Adaptive Knowledge Accumulation
Real-time Person Re-identification at the Edge: A Mixed Precision Approach
Devil's in the Details: Aligning Visual Clues for Conditional Embedding in Person Re-Identification
Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training
Rethinking Temporal Fusion for Video-based Person Re-identification on Semantic and Time Aspect
Camera-aware Proxies for Unsupervised Person Re-Identification
CLIP-based Camera-Agnostic Feature Learning for Intra-camera Person Re-Identification
Adaptive Threshold for Online Object Recognition and Re-identification Tasks
Invisible Backdoor Attack with Dynamic Triggers against Person Re-identification
Multi-task Learning with Coarse Priors for Robust Part-aware Person Re-identification
Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer
DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations
Graph Convolution for Re-ranking in Person Re-identification
Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians
Deep Metric Learning by Online Soft Mining and Class-Aware Attention
Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective
Enhancing Person Re-identification in a Self-trained Subspace
Person Re-identification with Correspondence Structure Learning
Deep Group-shuffling Random Walk for Person Re-identification
Multiple Expert Brainstorming for Domain Adaptive Person Re-identification
Feature Erasing and Diffusion Network for Occluded Person Re-Identification
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.