{"total":19,"rows":[{"id":"2212.05767","title":"A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal","created":"2022-12-12","cited_by_count":106,"area":null},{"id":"2307.11471","title":"Robust Visual Question Answering: Datasets, Methods, and Future Challenges","created":"2023-07-21","cited_by_count":23,"area":null},{"id":"2205.11501","title":"VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering","created":"2022-05-23","cited_by_count":22,"area":null},{"id":"2303.01903","title":"Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering","created":"2023-03-03","cited_by_count":21,"area":null},{"id":"2302.11509","title":"Construction of Knowledge Graphs: State and Challenges","created":"2023-02-22","cited_by_count":12,"area":null},{"id":"2305.06407","title":"Combo of Thinking and Observing for Outside-Knowledge VQA","created":"2023-05-10","cited_by_count":9,"area":null},{"id":"2402.02503","title":"GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering","created":"2024-02-04","cited_by_count":9,"area":null},{"id":"2403.14121","title":"External Knowledge Enhanced 3D Scene Generation from Sketch","created":"2024-03-21","cited_by_count":9,"area":null},{"id":"2211.00732","title":"Kuaipedia: a Large-scale Multi-modal Short-video Encyclopedia","created":"2022-10-28","cited_by_count":8,"area":null},{"id":"2406.01906","title":"ProGEO: Generating Prompts through Image-Text Contrastive Learning for Visual Geo-localization","created":"2024-06-04","cited_by_count":6,"area":null},{"id":"2301.00351","title":"Skew Class-balanced Re-weighting for Unbiased Scene Graph Generation","created":"2023-01-01","cited_by_count":5,"area":null},{"id":"2305.14485","title":"Knowledge Graphs Querying","created":"2023-05-23","cited_by_count":5,"area":null},{"id":"2310.18804","title":"Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting","created":"2023-10-28","cited_by_count":5,"area":null},{"id":"2407.21038","title":"Advancing Chart Question Answering with Robust Chart Component Recognition","created":"2024-07-19","cited_by_count":5,"area":null},{"id":"2409.14319","title":"Scene-Text Grounding for Text-Based Video Question Answering","created":"2024-09-22","cited_by_count":5,"area":null},{"id":"2309.01955","title":"A Survey on Interpretable Cross-modal Reasoning","created":"2023-09-05","cited_by_count":2,"area":null},{"id":"2410.23570","title":"Phrase Decoupling Cross-Modal Hierarchical Matching and Progressive Position Correction for Visual Grounding","created":"2024-10-31","cited_by_count":2,"area":null},{"id":"2507.04333","title":"Computed Tomography Visual Question Answering with Cross-modal Feature Graphing","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2407.04255","title":"Second Place Solution of WSDM2023 Toloka Visual Question Answering Challenge","created":"2024-07-05","cited_by_count":0,"area":null}],"next_cursor":null}