Research map / Detection and segmentation / Tracking
Hierarchical Feature Embedding for Visual Tracking
Zhixiong Pi, Weitao Wan, Chong Sun, Changxin Gao, Nong Sang, Chen Li
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 category classification alone (ablation) | DiMP18 · LaSOT | AUC (%): 53.5 -> 54.0 | Improved |
| add category classification alone (ablation) | SuperDiMP · OTB100 | AUC (%): 70.1 -> 69.7 | Hurt |
| add category encoder on top of category classification (ablation) | DiMP18 · LaSOT | AUC (%): 54.0 -> 56.8 | Improved |
| add category encoder on top of category classification (ablation) | SuperDiMP · LaSOT | AUC (%): 63.8 -> 64.8 | Improved |
| add video-level contrastive learning (ablation) | DiMP18 · LaSOT | AUC (%): 53.5 -> 57.0 | Improved |
| add video-level contrastive learning (ablation) | DiMP18 · OTB100 | AUC (%): 66.0 -> 68.4 | Improved |
| add instance encoder on top of contrastive learning (ablation) | DiMP18 · LaSOT | AUC (%): 57.0 -> 57.8 | Improved |
| add instance-aware module to category-aware module (ablation) | DiMP18 · LaSOT | AUC (%): 56.8 -> 59.2 | Improved |
| add instance-aware module to category-aware module (ablation) | SuperDiMP · LaSOT | AUC (%): 64.8 -> 66.2 | Improved |
| add momentum contrast to contrastive learning (ablation) | CIA18 · OTB100 | AUC (%): 65.8 -> 70.1 | Improved |
| add momentum contrast to contrastive learning (ablation) | CIA18 · LaSOT | AUC (%): 57.4 -> 59.2 | Improved |
| train with known category labels (70 LaSOT categories) (ablation) | CIA18 · LaSOT | AUC (%): 58.5 -> 59.2 | Improved |
Closest papers by meaning
- From Detection to Association: Learning Discriminative Object Embeddings for Multi-Object Tracking (CVPR 2026 · similarity 0.90)
- Robust Visual Tracking via Hierarchical Convolutional Features (TPAMI 2018 · similarity 0.89)
- Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision (NeurIPS 2025 · similarity 0.89)
- Self-Supervised Visual Representation Learning from Hierarchical Grouping (NeurIPS 2020 · similarity 0.89)
- VastTrack: Vast Category Visual Object Tracking (NeurIPS 2024 · similarity 0.88)
- Unifying Visual and Vision-Language Tracking via Contrastive Learning (AAAI 2024 · similarity 0.87)
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.
