AI Paper Atlas

Research map / Detection and segmentation / Tracking

Rethinking Two-Stage Referring-by-Tracking in Referring Multi-Object Tracking: Make it Strong Again

Weize Li, Yunhao Du, Qixiang Yin, Zhicheng Zhao, Fei Su

CVPR 2026 · Detection and segmentation › Tracking · approach: Association cues for online MOT

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 changedWhereMeasuredEffect
add C-Hook sampling-based feature construction to iKUN-style pipeline (ablation)FlexHook-iKUN · Refer-KITTI-V2HOTA: 10.32 -> 34.49Improved
replace cosine similarity with Pairwise Correspondence Decoder (ablation)FlexHook-iKUN · Refer-KITTI-V2HOTA: 34.49 -> 38.62Improved
add Temporal Integration with grid displacement instead of pooling (ablation)FlexHook-iKUN · Refer-KITTI-V2HOTA: 38.62 -> 39.19Improved
add Conditioning Enhancement with M=10 reference points (ablation)FlexHook-best · Refer-KITTI-V2HOTA: 41.94 -> 42.53Improved
add Conditioning Enhancement with M=10 (ablation)FlexHook-CLIP · Refer-KITTI-V2HOTA: 40.59 -> 41.42Improved
increase reference points from 10 to 30 (ablation)FlexHook-best · Refer-KITTI-V2HOTA: 42.53 -> 41.56Hurt
add noise augmentation in Neighboring Grid Sampling (ablation)FlexHook-best (no enhancement) · Refer-KITTI-V2HOTA: 40.65 -> 41.94Improved
freeze visual backbone and text encoder (ablation)FlexHook-best · Refer-KITTI-V2HOTA: 42.53 -> 40.86Hurt
freeze text encoder only (ablation)FlexHook-best · Refer-KITTI-V2HOTA: 42.53 -> 40.84Hurt
freeze visual backbone only (ablation)FlexHook-best · Refer-KITTI-V2HOTA: 42.53 -> 41.83Hurt
freeze encoders in CLIP-based FlexHook (ablation)FlexHook-CLIP · Refer-KITTI-V2HOTA: 41.42 -> 40.95No clear effect
use weaker detector and tracker (D-DETR and StrongSORT)FlexHook-best · Refer-KITTI-V2HOTA: 42.53 -> 40.73Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most 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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy