Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models
원문 초록
Textual-visual cross-modal retrieval has been a hot research topic in both computer vision and natural language processing communities. Learning appropriate representations for multi-modal data is crucial for the cross-modal retrieval performance. Unlike existing image-text retrieval approaches that embed image-text pairs as single feature vectors in a common representational space, we propose to incorporate generative processes into the cross-modal feature embedding, through which we are able to learn not only the global abstract features but also the local grounded features. Extensive experiments show that our framework can well match images and sentences with complex content, and achieve the state-of-the-art cross-modal retrieval results on MSCOCO dataset.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Maximal Matching Matters: Preventing Representation Collapse for Robust Cross-Modal Retrieval
Global–Local Information Soft-Alignment for Cross-Modal Remote-Sensing Image–Text Retrieval
Dynamic Modality Interaction Modeling for Image-Text Retrieval
Adding simple structure at inference improves Vision-Language Compositionality
Distill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation
ESA: External Space Attention Aggregation for Image-Text Retrieval
토론
이 논문과 연결된 포럼 글이 아직 없습니다.