Papers › R-VQA: Learning Visual Relation Facts with Semantic Attention for Visual Question Answering

R-VQA: Learning Visual Relation Facts with Semantic Attention for Visual Question Answering

24 May 2018arXiv:1805.09701archive 2025-07-28

Pan Lu, Lei Ji, Wei zhang, Nan Duan, Ming Zhou, Jianyong Wang

Recently, Visual Question Answering (VQA) has emerged as one of the most significant tasks in multimodal learning as it requires understanding both visual and textual modalities. Existing methods mainly rely on extracting image and question features to learn their joint feature embedding via multimodal fusion or attention mechanism. Some recent studies utilize external VQA-independent models to detect candidate entities or attributes in images, which serve as semantic knowledge complementary to the VQA task. However, these candidate entities or attributes might be unrelated to the VQA task and have limited semantic capacities. To better utilize semantic knowledge in images, we propose a novel framework to learn visual relation facts for VQA. Specifically, we build up a Relation-VQA (R-VQA) dataset based on the Visual Genome dataset via a semantic similarity module, in which each data consists of an image, a corresponding question, a correct answer and a supporting relation fact. A well-defined relation detector is then adopted to predict visual question-related relation facts. We further propose a multi-step attention model composed of visual attention and semantic attention sequentially to extract related visual knowledge and semantic knowledge. We conduct comprehensive experiments on the two benchmark datasets, demonstrating that our model achieves state-of-the-art performance and verifying the benefit of considering visual relation facts.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

lupantech/rvqa officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Question AnsweringSemantic SimilaritySemantic Textual SimilarityVisual Question AnsweringVisual Question Answering (VQA)

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Question Answering (VQA) COCO Visual Question Answering (VQA) real images 1.0 multiple choice RelAtt Percentage correct 69.60 #3 of 10 Archive leaderboard report
Visual Question Answering (VQA) COCO Visual Question Answering (VQA) real images 1.0 open ended RelAtt Percentage correct 65.69 #4 of 14 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections