Research map / Video / Video segmentation and tracking
AR2-4FV: Anchored Referring and Re-identification for Long-Term Grounding in Fixed-View Videos
Teng Yan, Yihan Liu, Jiongxu Chen, Teng Wang, Jiaqi Li, Bingzhuo Zhong
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 Anchor Map, ReID-Gating and re-entry prior to the baseline (ablation) | AR2-4FV · AR2-4FV-Bench | RCR: 0.67 -> 0.75 | Improved |
| add Anchor Map, ReID-Gating and re-entry prior to the baseline (ablation) | AR2-4FV · AR2-4FV-Bench | RCL (frames): 27.1 -> 20.1 | Improved |
| add Anchor Map, ReID-Gating and re-entry prior to the baseline (ablation) | AR2-4FV · AR2-4FV-Bench | IDF1: 61.2 -> 64.8 | Improved |
| add Anchor Map, ReID-Gating and re-entry prior to the baseline (ablation) | AR2-4FV · AR2-4FV-Bench | mIoU: 63.2 -> 66.9 | Improved |
| add Anchor Map, ReID-Gating and re-entry prior to the baseline (ablation) | AR2-4FV · AR2-4FV-Bench | mAP: 45.2 -> 49.2 | Improved |
| add anchor-based re-entry prior (ablation) | AR2-4FV · AR2-4FV-Bench | RCR / RCL | Improved |
| add ReID-Gating (ablation) | AR2-4FV · AR2-4FV-Bench | IDF1 | Improved |
| replace best baseline (DUTrack) with AR2-4FV | AR2-4FV · AR2-4FV-Bench | RCR: 0.69 -> 0.75 | Improved |
| replace best baseline (DUTrack) with AR2-4FV | AR2-4FV · AR2-4FV-Bench | RCL (frames): 25.8 -> 20.1 | 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.
- OnlineRefer — OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation (ICCV 2023) · better on 2 of 2 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
- ReWind: Understanding Long Videos with Instructed Learnable Memory (CVPR 2025 · similarity 0.86)
- APL: Anchor-based Prompt Learning for One-stage Weakly Supervised Referring Expression Comprehension (ECCV 2024 · similarity 0.85)
- LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding (NeurIPS 2024 · similarity 0.84)
- Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks (ICLR 2026 · similarity 0.84)
- Remember Me: Bridging the Long-Range Gap in LVLMs with Three-Step Inference-Only Decay Resilience Strategies (AAAI 2026 · similarity 0.84)
- Referencing Where to Focus: Improving Visual Grounding with Referential Query (NeurIPS 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.
