AI Paper Atlas

Research map / Detection and segmentation / Tracking

Mode-Conditioned Residual Calibration for Multi-Object Tracking

Muyu Li, Henan Hu, Deepak Jain, Xudong Zhao

ECCV 2026 · Detection and segmentation › Tracking · approach: Memory and correlation-based MOT · 0 citations (OpenAlex)

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 prototype-based error refinement (ablation)CAMELTrack · DanceTrack valHOTA: 66.8 -> 67.6Improved
add residual vector quantization (ablation)CAMELTrack + PR · DanceTrack valHOTA: 67.6 -> 67.9Improved
add uncertainty-gated denoiser (ablation)CAMELTrack + PR + VQ · DanceTrack valHOTA: 67.9 -> 69.0Improved
add motion cues to the mode classifier (ablation)MCRC · DanceTrack valHOTA: 68.0 -> 69.0Improved
add geometry cues (ablation)MCRC · DanceTrack valHOTA: 68.4 -> 69.0Improved
add confidence cues (ablation)MCRC · DanceTrack valHOTA: 68.7 -> 69.0Improved
use 6 prototype clusters instead of 3 (ablation)MCRC · DanceTrack valHOTA: 68.2 -> 69.0Improved
use 9 or 12 clusters instead of 6 (ablation)MCRC · DanceTrack valHOTA: 69.0 -> 69.1 (9 clusters), 69.0 (12 clusters)No clear effect
add magnitude clip to margin test in denoiser acceptance (ablation)MCRC denoiser · DanceTrack valHOTA: 68.5 -> 69.0Improved
use two-level 2x256 codebook instead of 1x64 (ablation)residual VQ · DanceTrack valHOTA: 67.4 -> 69.0Improved
double codebook from 2x128 to 2x256 (ablation)residual VQ · DanceTrack valHOTA: 68.9 -> 69.0No clear effect
align VQ codes to error-mode clusters (ablation)residual VQ · DanceTrack valHOTA: 68.7 -> 69.0Improved

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