AI Paper Atlas

Research map / Video / Video segmentation and tracking

DisenQ: Disentangling Q-Former for Activity-Biometrics

Shehreen Azad, Yogesh Singh Rawat

ICCV 2025 · Video › Video segmentation and tracking · approach: Spatial-temporal video person re-identification · 1 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 text encoder supervision to vision encoder (ablation)DisenQ · NTU RGB-ABRank-1: 73.2 -> 77.7Improved
add DisenQ on top of text encoder (ablation)DisenQ · NTU RGB-ABRank-1: 77.7 -> 82.2Improved
add DisenQ on top of text encoder (ablation)DisenQ · Charades-ABRank-1: 46.5 -> 49.9Improved
disentangle biometrics, non-biometrics and motion versus none (ablation)DisenQ · NTU RGB-ABRank-1: 74.2 -> 82.2Improved
add motion disentanglement to biometrics/non-biometrics split (ablation)DisenQ · NTU RGB-ABRank-1: 76.6 -> 82.2Improved
add non-biometrics disentanglement to biometrics/motion split (ablation)DisenQ · NTU RGB-ABRank-1: 79.2 -> 82.2Improved
combine motion with biometrics feature at inference (ablation)DisenQ · NTU RGB-ABRank-1: 80.4 -> 82.2Improved
use non-biometrics feature for matching (ablation)DisenQ · NTU RGB-ABRank-1: 82.2 -> 3.8Hurt
use random clothing text instead of VLM non-biometrics descriptions (ablation)DisenQ · NTU RGB-ABRank-1: 9.2% dropHurt
use three independent Q-Formers instead of unified DisenQ (ablation)DisenQ · NTU RGB-ABRank-1: 0.23% gain with tripled parametersNo clear effect
swap EVA-CLIP ViT-G/14 for SigLIP-L (ablation)DisenQ · NTU RGB-ABmAP: 43.8 -> 41.6Hurt
swap LLaVA 1.5 for GPT-4V as VLM (ablation)DisenQ · NTU RGB-ABRank-1: 82.2 -> 82.3No clear effect

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