Dual-Order Cross-Modal Fusion with Increment-Decrement Guidance for Composed Image Retrieval
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 4787-4796
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62407010)
- Natural Science Research Foundation of Jilin Province of China (20260102306JC)
This publication has 9 references indexed in Scilit:
- Leveraging Large Vision-Language Model as User Intent-Aware Encoder for Composed Image RetrievalProceedings of the AAAI Conference on Artificial Intelligence, 2025
- ENCODER: Entity Mining and Modification Relation Binding for Composed Image RetrievalProceedings of the AAAI Conference on Artificial Intelligence, 2025
- CoVR: Learning Composed Video Retrieval from Web Video CaptionsProceedings of the AAAI Conference on Artificial Intelligence, 2024
- Decomposing Semantic Shifts for Composed Image RetrievalProceedings of the AAAI Conference on Artificial Intelligence, 2024
- Data Roaming and Quality Assessment for Composed Image RetrievalProceedings of the AAAI Conference on Artificial Intelligence, 2024
- An End-To-End Graph Attention Network Hashing for Cross-Modal Retrieval2024
- Self-Training Boosted Multi-Factor Matching Network for Composed Image RetrievalIEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
- Composed Image Retrieval via Explicit Erasure and Replenishment With Semantic AlignmentIEEE Transactions on Image Processing, 2022
- Conditioned and composed image retrieval combining and partially fine-tuning CLIP-based features2022