Research map / Detection and segmentation / Tracking
Deep Affinity Network for Multiple Object Tracking
Shijie Sun, Naveed Akhtar, Huansheng Song, Ajmal Saeed Mian, Mubarak A. Shah
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use DAN online tracker versus best prior online tracker | DAN · MOT17 | MOTA: 48.0439 -> 52.4224 | Improved |
| use DAN versus best prior online tracker | DAN · MOT17 | MOTAL: 48.7518 -> 53.916 | Improved |
| DAN has more identity switches than prior trackers | DAN · MOT17 | ID switches: 3998 -> 8431 | Hurt |
| apply MOT17-trained DAN directly to MOT15 without fine-tuning versus CDA-DDAL | DAN · MOT15 | MOTA: 32.80 -> 38.30 | Improved |
| use CompACT instead of EB detector | DAN · UA-DETRAC | PR-MOTA: 18.6 | Mixed |
| use RCNN instead of EB detector | DAN · UA-DETRAC | PR-MOTAP: 15.1 and 37.1 | Mixed |
Closest papers by meaning
- Learnable Graph Matching: Incorporating Graph Partitioning With Deep Feature Learning for Multiple Object Tracking (CVPR 2021 · similarity 0.92)
- Simultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking (ECCV 2020 · similarity 0.91)
- A Unified Object Motion and Affinity Model for Online Multi-Object Tracking (CVPR 2020 · similarity 0.91)
- Multiple Object Tracking as ID Prediction (CVPR 2025 · similarity 0.90)
- MOTS: Multi-Object Tracking and Segmentation (CVPR 2019 · similarity 0.90)
- DiffusionTrack: Diffusion Model for Multi-Object Tracking (AAAI 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
