AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

CoCo-IR: Conversational Composed Image Retrieval

Shengcao Cao, Tanmaya Dabral, Zhongli Ding, Madhuri Shanbhogue, Kaifeng Chen, Zhe Li, Mojtaba Seyedhosseini, Liang-Yan Gui, Yu-Xiong Wang

ECCV 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Composed and text-based image 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
add LMM-verified hard negatives to mixed-source training data (ablation)TIE-4B · Fashion IQR@10: 33.7 -> 40.1Improved
add LMM-verified hard negatives to mixed-source training data (ablation)TIE-4B · CoCo-IR 1-turnR@1: 67.7 -> 75.4Improved
add hard negatives to feature-based data (ablation)TIE-4B · CIRCOmAP@5: 33.2 -> 38.0Improved
add hard negatives to metadata-based data (ablation)TIE-4B · CIRRR@1: 36.6 -> 34.3Hurt
add hard negatives to metadata-based data (ablation)TIE-4B · CoCo-IR 1-turnR@1: 60.7 -> 56.4Hurt
mix feature-based and metadata-based data instead of feature-based only (with hard negatives) (ablation)TIE-4B · Fashion IQR@10: 38.0 -> 40.1Improved
mix feature-based and metadata-based data instead of feature-based only (with hard negatives) (ablation)TIE-4B · CIRCOmAP@5: 38.0 -> 37.8No clear effect
mix sources instead of metadata-only data (no hard negatives) (ablation)TIE-4B · CoCo-IR 1-turnR@1: 60.7 -> 67.7Improved
scale training data from 320K to 2.56M samples (ablation)TIE-4B · CIRRR@1: 34.8 -> 37.7Improved
scale training data from 320K to 2.56M samples (ablation)TIE-4B · CIRCOmAP@5: 36.7 -> 37.8Mixed
scale training data from 1.28M to 2.56M samples (ablation)TIE-4B · Fashion IQR@10: 40.0 -> 40.1No clear effect
scale model from TIE-4B to TIE-12BTIE · CoCo-IR 4-turnR@1: 31.1 -> 44.1Improved

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