Research map / Detection and segmentation / Tracking
Tracking Without Re-recognition in Humans and Machines
Read the paperCheck 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 |
|---|---|---|---|
| Add the InT circuit to TransT and train with 8-frame sequences | TransT · TrackingNet | P_norm: 86.7 -> 87.48 | Helped |
| Add the InT circuit to TransT and train with 8-frame sequences | TransT · LaSOT | P_norm: 73.8 -> 74.0 | Helped |
| Add the InT circuit to TransT and train with 8-frame sequences | TransT · GOT-10K | AO: 72.3 -> 72.2 | Hurt |
| Add the InT circuit to TransT and train with 8-frame sequences | TransT · GOT-10K Color | AO: 40.7 -> 43.1 | Helped |
| Add the InT circuit to TransT and train with 8-frame sequences | TransT · GOT-10K rColor | AO: 57.5 -> 62.5 | Helped |
| Add the InT circuit to TransT and train with 8-frame sequences | TransT · GOT-10K Occl. | AO: 55.2 -> 56.9 | Helped |
| Train InT+TransT on 8-frame rather than 1-frame sequences (ablation) | InT+TransT · GOT-10K rColor | AO: 37.8 -> 62.5 | Helped |
| Train InT+TransT on 8-frame rather than 1-frame sequences (ablation) | InT+TransT · TrackingNet | P_norm: 87.3 -> 87.5 | Helped |
| Train InT+TransT on 8-frame rather than 1-frame sequences (ablation) | InT+TransT · GOT-10K | AO: 70.0 -> 72.2 | Helped |
| Replace the sigmoid attention activation with spatial softmax, limiting attention to one spatial distribution (ablation) | InT · PathTracker | accuracy | Hurt |
| Replace softplus rectifications with tanh (ablation) | InT · PathTracker 25 distractors, 64 frames | accuracy | Hurt |
| Remove attention units (ablation) | InT · PathTracker | accuracy | Hurt |
Closest papers by meaning
- Tracking objects that change in appearance with phase synchrony (ICLR 2025 · similarity 0.89)
- Leveraging Saccades to Learn Smooth Pursuit: A Self-Organizing Motion Tracking Model Using Restricted Boltzmann Machines (AAAI 2017 · similarity 0.88)
- Flow Snapshot Neurons in Action: Deep Neural Networks Generalize to Biological Motion Perception (NeurIPS 2024 · similarity 0.87)
- Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision (NeurIPS 2025 · similarity 0.86)
- VastTrack: Vast Category Visual Object Tracking (NeurIPS 2024 · similarity 0.85)
- Beyond Accuracy: Tracking more like Human via Visual Search (NeurIPS 2024 · 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.