[ICCV 2023] - Zero-shot Composed Image Retrieval with Textual Inversion

Official Pytorch implementation of LinCIR: Language-only Training of Zero-shot Composed Image Retrieval (CVPR 2024)

Official repository of ICCV 2021 - Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models

Official PyTorch implementation of the paper "CoVR: Learning Composed Video Retrieval from Web Video Captions".

Official Pytorch implementation of "CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion" (TMLR 2024)

[ICCV 2023] - Composed Image Retrieval on Common Objects in context (CIRCO) dataset

[BMVC 2023] Zero-shot Composed Text-Image Retrieval

Toward Universal Multimodal Embedding

Official PyTorch implementation of the WACV 2025 Oral paper "Composed Image Retrieval for Training-FREE DOMain Conversion".

[ACM MM 2024] Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives

text-only training or language-free training for multimodal tasks (image/audio/video caption, retrieval, text2image)

Official repository of the LaSCo dataset

[CVPR 2025] Official Pytorch implementation of "Learning with Noisy Triplet Correspondence for Composed Image Retrieval".

Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity (TAAI 2024)