AI Paper Atlas

Research map / Video / Video-language understanding

Compositional Transformation Reasoning for Composed Video Retrieval

Sihong Huang, Jiaxin Wu, Dongmei Jiang, Yi Cai, Yaowei Wang, Xiaoyong Wei

CVPR 2026 · Video › Video-language understanding · approach: Text-video retrieval

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
use pairwise relative comparison instead of absolute relevance scoring in MLLM (ablation)MoRe · EgoCVR (global)R@1: 7.4 -> 20.4Improved
replace original modification text with predicted fine-grained target semantics for retrieval (ablation)MoRe · EgoCVR text-to-videoR@1: 0.9 -> 5.9Improved
replace original modification text with predicted fine-grained target semantics for retrieval (ablation)MoRe · WebVid-CoVR text-to-videoR@1: 24.4 -> 47.6Improved
use predicted semantics in ROVCS with MLLM reasoning stage (ablation)MoRe · EgoCVR (global)R@1: 16.3 -> 20.4Improved
use predicted semantics in ROVCS with MLLM reasoning stage (ablation)MoRe · WebVid-CoVRR@1: 60.9 -> 63.0Improved
add MLLM pairwise reasoning replacing text-similarity stage 2 (with ROVCS) (ablation)MoRe · EgoCVR (global)R@1: 8.4 -> 20.4Improved
add ROVCS candidate selection over visual-similarity stage 1 (with MLLM reasoning) (ablation)MoRe · EgoCVR (global)R@1: 15.8 -> 20.4Improved
add ROVCS candidate selection over visual-similarity stage 1 (with MLLM reasoning) (ablation)MoRe · WebVid-CoVRR@1: 60.3 -> 63.0Improved
ROVCS alone (with text-similarity stage 2) vs TFR-CVR baseline (ablation)MoRe · EgoCVR (global)R@1: 14.1 -> 8.4Hurt
ROVCS candidate selection instead of visual similarity (ablation)MoRe · EgoCVR target-in-candidate ratiotarget in candidate set (%): 64.5 -> 74.5Improved
reduce candidates K from 15 to 10 (ablation)MoRe · EgoCVR (global)R@1: 20.4 -> 17.2; runtime 23.9s -> 10.4sMixed
Swiss tournament instead of full pairwise comparison (ablation)MoRe · EgoCVR (global)R@1: 20.4 -> 17.7; runtime 23.9s -> 12.8sMixed

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