Research map / Detection and segmentation / Tracking
Language Decoupling with Fine-grained Knowledge Guidance for Referring Multi-object Tracking
Guangyao Li, Siping Zhuang, Yajun Jian, Yan Yan, Hanzi Wang
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 MPA module to base (ablation) | DKGTrack · Refer-KITTI val | HOTA: 50.31 -> 51.07 | Improved |
| add SSE module to base (ablation) | DKGTrack · Refer-KITTI val | HOTA: 50.31 -> 51.36 | Improved |
| add SSE module to base (ablation) | DKGTrack · Refer-KITTI val | DetA: 38.49 -> 40.53 | Improved |
| add SSE module to base (ablation) | DKGTrack · Refer-KITTI val | AssA: 65.93 -> 65.58 | Hurt |
| add SSE on top of MPA (ablation) | DKGTrack · Refer-KITTI val | HOTA: 51.07 -> 52.08 | Improved |
| add SSE on top of MPA (ablation) | DKGTrack · Refer-KITTI val | AssA: 66.20 -> 66.04 | Hurt |
| initialize queries with sentence embedding instead of word-level features (ablation) | DKGTrack · Refer-KITTI val | HOTA: 50.51 -> 51.36 | Improved |
| initialize queries with sentence embedding instead of localized descriptions only (ablation) | DKGTrack · Refer-KITTI val | HOTA: 50.87 -> 51.36 | Improved |
| set temperature beta to 0.5 instead of 0.1 (ablation) | DKGTrack MPA · Refer-KITTI val | HOTA: 50.33 -> 51.07 | Improved |
| set temperature beta to 0.5 instead of 0.9 (ablation) | DKGTrack MPA · Refer-KITTI val | HOTA: 50.21 -> 51.07 | Improved |
| use DKGTrack instead of TempRMOT | DKGTrack · Refer-KITTI test | HOTA: 50.31 -> 52.08 | Improved |
| use DKGTrack instead of TempRMOT | DKGTrack · Refer-KITTI-V2 test | HOTA: 33.79 -> 35.26 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- iKUN — iKUN: Speak to Trackers without Retraining (CVPR 2024) · better on 3 of 4 shared results
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
- iKUN: Speak to Trackers without Retraining (CVPR 2024 · similarity 0.89)
- Cross-View Referring Multi-Object Tracking (AAAI 2025 · similarity 0.88)
- Unifying Visual and Vision-Language Tracking via Contrastive Learning (AAAI 2024 · similarity 0.88)
- ChatTracker: Enhancing Visual Tracking Performance via Chatting with Multimodal Large Language Model (NeurIPS 2024 · similarity 0.87)
- HFF-Tracker: A Hierarchical Fine-grained Fusion Tracker for Referring Multi-Object Tracking (AAAI 2025 · similarity 0.87)
- OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer (ICLR 2025 · similarity 0.86)
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.
