AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Generating a Paracosm for Training-Free Zero-Shot Composed Image Retrieval

Tong Wang, Yunhan Zhao, Shu Kong

ECCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 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 synthetic counterparts of database images (ablation)Paracosm (CLIP ViT-B/32) · CIRR testRecall@1: 27.93 -> 32.27Improved
add synthetic counterparts of database images (ablation)Paracosm (CLIP ViT-B/32) · CIRCO testmAP@5: 18.29 -> 26.10Improved
add modification text to the query feature (ablation)Paracosm (CLIP ViT-B/32) · CIRR testRecall@1: 24.60 -> 32.27Improved
add modification text to the query feature (ablation)Paracosm (CLIP ViT-B/32) · CIRCO testmAP@5: 16.57 -> 26.10Improved
add mental image to description-based query (ablation)Paracosm with synthetic counterparts, no t_mod · CIRR testRecall@1: 22.46 -> 24.60Improved
add mental image to description-based query (ablation)Paracosm with synthetic counterparts, no t_mod · CIRCO testmAP@5: 16.72 -> 16.57Hurt
edit the reference image instead of T2I generation for mental image (ablation)Paracosm · CIRR testRecall@1: 31.71 -> 32.27Improved
use LongCat-Image-Edit instead of Qwen-Image-Edit (ablation)Paracosm · CIRR testRecall@1: 32.27 -> 32.12No clear effect
use GPT-4o instead of Qwen2.5-VL for descriptions (ablation)Paracosm · CIRR testRecall@1: 32.27 -> 31.86No clear effect
add brief descriptions of database images (ablation)Paracosm · Fashion IQ valRecall@10: 26.14 -> 26.06No clear effect
add detailed descriptions of database images to matching (ablation)Paracosm · CIRR testRecall@1: 32.27 -> 28.33Hurt
replace CLIP with OpenCLIP ViT-B/32 backbone (ablation)Paracosm · CIRCO testmAP@5: 26.10 -> 31.31Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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