Learning Cross-modal Context Graph for Visual Grounding
Visual grounding is a ubiquitous building block in many vision-language tasks and yet remains challenging due to large variations in visual and linguistic features of grounding entities, strong context effect and the resulting semantic ambiguities. Prior works typically focus on learning representations of individual phrases with limited context information. To address their limitations, this paper proposes a language-guided graph representation to capture the global context of grounding entities and their relations, and develop a cross-modal graph matching strategy for the multiple-phrase visual grounding task. In particular, we introduce a modular graph neural network to compute context-aware representations of phrases and object proposals respectively via message propagation, followed by a graph-based matching module to generate globally consistent localization of grounding phrases. We train the entire graph neural network jointly in a two-stage strategy and evaluate it on the Flickr30K Entities benchmark. Extensive experiments show that our method outperforms the prior state of the arts by a sizable margin, evidencing the efficacy of our grounding framework. Code is available at https://github.com/youngfly11/LCMCG-PyTorch.
Code (1)
Tasks
Graph MatchingGraph Neural NetworkLanguage ModellingNatural Language Visual GroundingPhrase GroundingVisual GroundingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Learning Cross-modal Context Graph for Visual Grounding
Visual grounding is a ubiquitous building block in many vision-language tasks and yet remains challenging due to large variations in visual and linguistic features of grounding entities, strong context effect and the res…
Graph MatchingGraph Neural NetworkVisual GroundingCross-Modal Relationship Inference for Grounding Referring Expressions
Grounding referring expressions is a fundamental yet challenging task facilitating human-machine communication in the physical world. It locates the target object in an image on the basis of the comprehension of the rela…
Relationship-Embedded Representation Learning for Grounding Referring Expressions
Grounding referring expressions in images aims to locate the object instance in an image described by a referring expression. It involves a joint understanding of natural language and image content, and is essential for …
Referring ExpressionRepresentation LearningM$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) has recently been extended to multimodal settings, connecting multimodal large language models (MLLMs) with vast corpora of external knowledge such as multimodal knowledge graphs (MMK…
Multimodal ReasoningResponse GenerationKnowledge GraphsLocAnyMed: Vision-Language Grounding for Multimodal Medical Images
Medical visual grounding connects free-form clinical queries to spatial evidence in medical images and is an important component of interpretable medical artificial intelligence. However, general-purpose grounding models…
Visual Grounding