Research map / Detection and segmentation / Tracking
QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking
Tobias Fischer, T. Huang, Jiangmiao Pang, Linlu Qiu, Haofeng Chen, Trevor Darrell, Fisher Yu
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 |
|---|---|---|---|
| add quasi-dense matching (many negatives, one positive) (ablation) | QDTrack · BDD100K val (ablation, Faster R-CNN R50) | IDF1: 63.0 -> 66.8 | Improved |
| add multi-positive contrastive loss (ablation) | QDTrack · BDD100K val (ablation, Faster R-CNN R50) | IDF1: 66.8 -> 67.8 | Improved |
| replace cosine similarity with bi-softmax (ablation) | QDTrack · BDD100K val (ablation, Faster R-CNN R50) | IDF1: 67.8 -> 70.0 | Improved |
| add duplicate removal and backdrops (ablation) | QDTrack · BDD100K val (ablation, Faster R-CNN R50) | IDF1: 70.0 -> 71.5 | Improved |
| add all quasi-dense training and inference components (ablation) | QDTrack · BDD100K val (ablation, Faster R-CNN R50) | IDF1: 63.0 -> 71.5 | Improved |
| add IoU cue to appearance association (ablation) | QDTrack · BDD100K val | mMOTA: 36.6 -> 36.3 | No clear effect |
| add distance thresholding (ablation) | QDTrack · MOT17 val (half, ablation) | IDF1: 73.6 -> 74.5 | Improved |
| add tracklet merging (ablation) | QDTrack · MOT17 val (half, ablation) | IDF1: 74.5 -> 76.0 | Improved |
| add linear interpolation (ablation) | QDTrack · MOT17 val (half, ablation) | MOTA: 76.0 -> 76.8 | Improved |
| add stronger data augmentation to supervised video training (ablation) | QDTrack · BDD100K val | mMOTA: +1.2 points in mMOTA, +2.1 points in mIDF1 | Improved |
| train 2x schedule instead of 1x (ablation) | QDTrack (Faster R-CNN R50-FPN) · BDD100K val | MOTA: 65.7 -> 65.6 | No clear effect |
| use ResNet-101 instead of ResNet-50 (ablation) | QDTrack (Faster R-CNN) · BDD100K val | MOTA: 65.7 -> 66.2 | Improved |
Later papers that compared with this method
6 later accepted papers report QDTrack as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.
- SOVTrack: Open-Vocabulary Multi-Object Tracking with Self-Supervised Pseudo Labeling and Feature Distillation (ECCV 2026 · better on 4 of 4 shared results)
- Learning Pseudo 3D Representation for Ego-centric 2D Multiple Object Tracking (IJCV 2026 · better on 2 of 4 shared results)
- SelfMOTR: Revisiting MOTR with Self-Generating Detection Priors (ECCV 2026 · better on 0 of 1 shared result)
- Simple Cues Lead to a Strong Multi-Object Tracker (CVPR 2023 · better on 5 of 6 shared results)
- Unifying Short and Long-Term Tracking With Graph Hierarchies (CVPR 2023 · better on 1 of 1 shared result)
- Collaborative Tracking Learning for Frame-Rate-Insensitive Multi-Object Tracking (ICCV 2023 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- ByteTrack — ByteTrack: Multi-Object Tracking by Associating Every Detection Box (ECCV 2022) · better on 3 of 5 shared results
- MOTR — MOTR: End-to-End Multiple-Object Tracking with TRansformer (ECCV 2022) · better on 0 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Tracking (AAAI 2024 · similarity 0.88)
- ODTrack: Online Dense Temporal Token Learning for Visual Tracking (AAAI 2024 · similarity 0.87)
- DiffusionTrack: Diffusion Model for Multi-Object Tracking (AAAI 2024 · similarity 0.86)
- Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision (NeurIPS 2025 · similarity 0.86)
- Matching Anything by Segmenting Anything (CVPR 2024 · similarity 0.85)
- Focusing on Tracks for Online Multi-Object Tracking (CVPR 2025 · similarity 0.85)
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.
