Fine-grained Textual Inversion Network for Zero-Shot Composed Image Retrieval
Composed Image Retrieval (CIR) allows users to search target images with a multimodal
query, comprising a reference image and a modification text that describes the user's …
query, comprising a reference image and a modification text that describes the user's …
Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval
Abstract Composed Image Retrieval (CIR) is a task that retrieves images similar to a query
based on a provided textual modification. Current techniques rely on supervised learning for …
based on a provided textual modification. Current techniques rely on supervised learning for …
Simple but Effective Raw-Data Level Multimodal Fusion for Composed Image Retrieval
Composed image retrieval (CIR) aims to retrieve the target image based on a multimodal
query, ie, a reference image paired with corresponding modification text. Recent CIR studies …
query, ie, a reference image paired with corresponding modification text. Recent CIR studies …
Pseudo-triplet Guided Few-shot Composed Image Retrieval
Composed Image Retrieval (CIR) is a challenging task that aims to retrieve the target image
based on a multimodal query, ie, a reference image and its corresponding modification text …
based on a multimodal query, ie, a reference image and its corresponding modification text …
Self-Distilled Dynamic Fusion Network for Language-Based Fashion Retrieval
Y Wu, H Li, F Wang, Y Zhang… - ICASSP 2024-2024 IEEE …, 2024 - ieeexplore.ieee.org
In the domain of language-based fashion image retrieval, pinpointing the desired fashion
item using both a reference image and its accompanying textual description is an intriguing …
item using both a reference image and its accompanying textual description is an intriguing …