Zero-shot composed image retrieval (ZS-CIR) methods often use large vision-language models (LVLMs) to represent an image-text query comprising a reference image and a modification instruction. However, semantically equivalent instructions can alter the generated representations and final rankings. An individual retriev...
Composed image retrieval (CIR) aims to retrieve images that satisfy a user-specified modification while preserving relevant visual content from a reference image. Collecting target images for this purpose is costly, motivating zero-shot CIR methods that instead use target captions as supervision. However, target captio...
M UL V EC is proposed, a role-aware method whose compiler produces a structured query record that is mapped to four retrieval roles: Global describes the full target, Desired states what should appear, Preserve states what should remain, and Forbidden states what should disappear.
ZS-CIR aims to retrieve a target image from a reference image and a modification text without paired supervision, typically by encoding composed queries as text-dominant representations within the image-text matching space of VLPs. However, queries reconstructed by visual pseudo-word learning or MLLM-based target reaso...
This work fuse DINOv3 and CleanDIFT representations into a perception encoder and align it with RoBERTa-L, yielding a text-aligned model TDDN that preserves this perceptual advantage and leads on segmentation benchmarks among general-purpose contrastive encoders, including SigLIP.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
