检测结果进行目标关联调研
- 1.基于 群体重识别
- 2.基于 多目标跟踪（图匹配）
- 3. 计算梁振间的偏移
- 4.大模型
- 5.跨相机多目标跟踪
- 6.图+VLM or correspondence matching
-
- 2024（×）
- 2025 （×）
-
- Multimodal Knowledge Graph Completion Using CLIP-Enhanced Hyper-Node Relational Graph Attention Networks
- CLIP-Cluster: CLIP-Guided Attribute Hallucination for Face Clustering
- CLIP-Clique: Graph-based Correspondence Matching Augmented by Vision Language Models for Object-based Global Localization(IRAL 开源)
- CLIP-Loc: Multi-modal Landmark Association for Global Localization in Object-based Maps（2024 iros）
- 7.自动驾驶
- 8.开放词汇检测
- 9.语义匹配（semantic correspondence）
- 10.clip和reid
- 11.跨相机目标关联
-
- 2024
-
- MVUDA: Unsupervised Domain Adaptation for Multi-view Pedestrian Detection（cvpr）
- An end-to-end tracking framework via multi-view and temporal feature aggregation(cvir)
- Enhancing Multi-Camera Gymnast Tracking Through Domain Knowledge Integration
- PPM: A boolean optimizer for data association in multi-view pedestrian detection(Pattern Recognition)（重点）
- Cross-Camera Data Association via GNN for Supervised Graph Clustering(cvpr)（重点）
- STCA: High-Altitude Tracking via Single-Drone Tracking and Cross-Drone Association(remote sense)
- 12.无相机参数的多视图检测/无相机参数的bev
- 2021
- 2024
- 2025
- 13.跨相机多目标关联/重识别（0321）
- 紧密相关
-
- 2024
-
- Robust Cross-Drone Multi-Target Association Using 3D Spatial Consistency （构建空间拓扑结构类似于lxd，依赖于传感器）
- Visio-Temporal Attention for Multi-Camera Multi-Target Association（2021cvpr，无校正相机）
- Features for multi-target multi-camera tracking and re-identification（2018 杜克大学）
- Adaptive Affinity for Associations in Multi-Target Multi-Camera Tracking
- Calibration-Free Cross-Camera Target Association Using Interaction Spatiotemporal Consistency（云里雾里，很复杂）
- City-Scale Multi-Camera Vehicle Tracking by Semantic Attribute Parsing and Cross-Camera Tracklet Matching（图gnn+时序轨迹匹配，无需相机姿态）
- Hierarchical Multi-Graphs Learning for Robust Group Re-Identification
- Multi-Vehicle Multi-Camera Tracking with Graph-Based Tracklet Features
1.基于 群体重识别
2021
Dotscn: Group re-identification via domain-transferred single and couple representation learning（TPAMI 开源）
Learning Multi-Attention Context Graph for Group-Based Re-Identification（TPAMI 开源）
2022
Uncertainty modeling with second-order transformer for group re-identification（AAAI）
2023
Similarity metric learning for RGB-infrared group re-identification(cvpr)
2024
Separable Spatial-Temporal Residual Graph for Cloth-Changing Group Re-Identification（TPAMI）
Unsupervised group re-identification via adaptive clustering-driven progressive learning(AAAI)
2025
A Comprehensive Review on Group Re-identification in Surveillance Videos
Group-CLIP Uncertainty Modeling for Group Re-Identification
2.基于 多目标跟踪（图匹配）
2020
[25031501] GSM: Graph Similarity Model for Multi-Object Tracking (CVPR 无代码 开山)
[25031504]GSTD:Joint Object Detection and Multi-Object Tracking with Graph Neural Networks/（cvpr 联合检测以及关联）
2021
[25031502] Learnable graph matching: Incorporating graph partitioning with deep feature learning for multiple object tracking（CVPR 开源）
[25031503]multiple target tracking with correlation learning(cvpr SITL)
3. 计算梁振间的偏移
4.大模型
OVTrack: Open-Vocabulary Multiple Object Tracking
最低0.47元/天 解锁文章
扫一扫
469
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
