Jing Tang
Other people with similar names: Jing Tang
Unverified author pages with similar names: Jing Tang
2026
Beyond Query Bias: Candidate-Aware Iterative Refinement for Zero-Shot Composed Image Retrieval
Nan Sun | Jing Tang | Lei Sun | Rui Chen | Yuxing Lu | Xiangxiang Chu | Hefei Ling | Yujun Cai
Findings of the Association for Computational Linguistics: ACL 2026
Nan Sun | Jing Tang | Lei Sun | Rui Chen | Yuxing Lu | Xiangxiang Chu | Hefei Ling | Yujun Cai
Findings of the Association for Computational Linguistics: ACL 2026
Zero-Shot Composed Image Retrieval (ZS-CIR) retrieves target images using a reference image and modification text without task-specific training. Existing methods typically rely on MLLMs to generate query vectors with pre-trained models like CLIP. However, those constructed queries suffer from inherent cognitive bias due to unknown candidate distribution. We propose CoRR, a training-free framework that reframes ZS-CIR as a self-correcting process through bias-aware query refinement. CoRR uses retrieved results as feedback to perceive the candidate distribution. With carefully designed CoT prompting, the MLLM inspects the retrieved candidates to identify intent misalignments in the query and then corrects them via Historical Query Fusion. We also introduce Retrieval-Driven Caption Optimization to provide context-aligned examples, reducing phrasing and style mismatches. Experiments on public benchmarks show that CoRR significantly outperforms other SOTA methods.