Research map / Detection and segmentation / Tracking
Multi-Object Tracking With Quadruplet Convolutional Neural Networks
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 Quad-CNN rather than NOMT | 2DMOT2015 tracking · 2DMOT2015 test | MOTA: 33.7 -> 33.8 | Helped |
| use Quad-CNN rather than NOMT | MOT16 tracking · MOT16 test | MOTA: 46.4 -> 44.1 | Hurt |
| add bounding-box regression (ablation) | Quad-CNN · 2DMOT2015 validation | MOTA: 13.6 -> 16.9 | Helped |
| learn feature weights rather than use constant weights (ablation) | Quad-CNN · 2DMOT2015 validation | MOTA: 14.3 -> 16.9 | Helped |
| slice pool5 features into upper and lower parts (ablation) | Quad-CNN · 2DMOT2015 validation | MOTA: 14.3 -> 16.9 | Helped |
| add sequence-specific embedding for position features (ablation) | Quad-CNN · 2DMOT2015 validation | MOTA: 15.2 -> 16.9 | Helped |
| use quadruplet loss rather than triplet loss (ablation) | Quad-CNN · 2DMOT2015 validation | MOTA: 16.1 -> 16.9 | Helped |
| use quadruplet loss rather than triplet loss (ablation) | Quad-CNN · 2DMOT2015 test | MOTA: 32.6 -> 33.8 | Helped |
| add bounding-box regression to the triplet variant (ablation) | TRIPLET · 2DMOT2015 test | MOTA: 29.4 -> 32.6 | Helped |
| learn feature weights rather than use constant weights in the triplet variant (ablation) | TRIPLET · 2DMOT2015 test | MOTA: 29.3 -> 32.6 | Helped |
Closest papers by meaning
- Learning Multi-Domain Convolutional Neural Networks for Visual Tracking (CVPR 2016 · similarity 0.88)
- Multiple Object Tracking With Correlation Learning (CVPR 2021 · similarity 0.87)
- From Detection to Association: Learning Discriminative Object Embeddings for Multi-Object Tracking (CVPR 2026 · similarity 0.86)
- ADA-Track: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Association (CVPR 2024 · similarity 0.85)
- Multiple Object Tracking as ID Prediction (CVPR 2025 · similarity 0.84)
- DiffusionTrack: Diffusion Model for Multi-Object Tracking (AAAI 2024 · similarity 0.84)
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.