{"total":39,"rows":[{"id":"2306.08640","title":"AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn","created":"2023-06-14","cited_by_count":97,"area":null},{"id":"2112.12494","title":"LaTr: Layout-Aware Transformer for Scene-Text VQA","created":"2021-12-23","cited_by_count":72,"area":null},{"id":"2209.13232","title":"A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective","created":"2022-09-27","cited_by_count":56,"area":null},{"id":"2209.03299","title":"Multimodal learning with graphs","created":"2022-09-07","cited_by_count":54,"area":null},{"id":"2208.12037","title":"Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task","created":"2022-08-24","cited_by_count":35,"area":null},{"id":"2311.16081","title":"ViT-Lens: Towards Omni-modal Representations","created":"2023-11-27","cited_by_count":29,"area":null},{"id":"2110.02526","title":"Coarse-to-Fine Reasoning for Visual Question Answering","created":"2021-10-06","cited_by_count":25,"area":null},{"id":"2104.00170","title":"Are Bias Mitigation Techniques for Deep Learning Effective?","created":"2021-04-01","cited_by_count":14,"area":null},{"id":"2108.08965","title":"Localize, Group, and Select: Boosting Text-VQA by Scene Text Modeling","created":"2021-08-20","cited_by_count":14,"area":null},{"id":"2302.03242","title":"Combating Online Misinformation Videos: Characterization, Detection, and Future Directions","created":"2023-02-07","cited_by_count":14,"area":null},{"id":"2305.13854","title":"The Evolution of Distributed Systems for Graph Neural Networks and their Origin in Graph Processing and Deep Learning: A Survey","created":"2023-05-23","cited_by_count":14,"area":null},{"id":"2406.18815","title":"MissionGNN: Hierarchical Multimodal GNN-based Weakly Supervised Video Anomaly Recognition with Mission-Specific Knowledge Graph Generation","created":"2024-06-27","cited_by_count":14,"area":null},{"id":"2208.01813","title":"TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation","created":"2022-08-03","cited_by_count":12,"area":null},{"id":"2107.11576","title":"X-GGM: Graph Generative Modeling for Out-of-Distribution Generalization in Visual Question Answering","created":"2021-07-24","cited_by_count":10,"area":null},{"id":"2303.03761","title":"Graph Neural Networks in Vision-Language Image Understanding: A Survey","created":"2023-03-07","cited_by_count":10,"area":null},{"id":"2309.11845","title":"TMac: Temporal Multi-Modal Graph Learning for Acoustic Event Classification","created":"2023-09-21","cited_by_count":9,"area":null},{"id":"2504.13112","title":"Hadamard product in deep learning: Introduction, Advances and Challenges","created":"2025-04-17","cited_by_count":9,"area":null},{"id":"2311.01620","title":"ACQUIRED: A Dataset for Answering Counterfactual Questions In Real-Life Videos","created":"2023-11-02","cited_by_count":8,"area":null},{"id":"2202.12478","title":"GAME-ON: Graph Attention Network based Multimodal Fusion for Fake News Detection","created":"2022-02-25","cited_by_count":7,"area":null},{"id":"2111.13361","title":"Geometric Multimodal Deep Learning with Multi-Scaled Graph Wavelet Convolutional Network","created":"2021-11-26","cited_by_count":6,"area":null},{"id":"2310.09147","title":"Exploring Sparse Spatial Relation in Graph Inference for Text-Based VQA","created":"2023-10-13","cited_by_count":6,"area":null},{"id":"2211.12950","title":"Look, Read and Ask: Learning to Ask Questions by Reading Text in Images","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2111.14547","title":"LiVLR: A Lightweight Visual-Linguistic Reasoning Framework for Video Question Answering","created":"2021-11-29","cited_by_count":4,"area":null},{"id":"2304.01603","title":"Locate Then Generate: Bridging Vision and Language with Bounding Box for Scene-Text VQA","created":"2023-04-04","cited_by_count":4,"area":null},{"id":"2311.08622","title":"Multiple-Question Multiple-Answer Text-VQA","created":"2023-11-15","cited_by_count":4,"area":null},{"id":"2410.22623","title":"PV-VTT: A Privacy-Centric Dataset for Mission-Specific Anomaly Detection and Natural Language Interpretation","created":"2024-10-30","cited_by_count":4,"area":null},{"id":"2104.14360","title":"Video Salient Object Detection via Adaptive Local-Global Refinement","created":"2021-04-29","cited_by_count":3,"area":null},{"id":"2109.02219","title":"Reasoning Graph Networks for Kinship Verification: from Star-shaped to Hierarchical","created":"2021-09-06","cited_by_count":3,"area":null},{"id":"2409.07889","title":"BLens: Contrastive Captioning of Binary Functions using Ensemble Embedding","created":"2024-09-12","cited_by_count":3,"area":null},{"id":"2501.04303","title":"Graph-Based Multimodal Contrastive Learning for Chart Question Answering","created":"2025-01-08","cited_by_count":3,"area":null},{"id":"2207.13242","title":"Uncertainty-based Visual Question Answering: Estimating Semantic Inconsistency between Image and Knowledge Base","created":"2022-07-27","cited_by_count":2,"area":null},{"id":"2212.08283","title":"SceneGATE: Scene-Graph based co-Attention networks for TExt visual question answering","created":"2022-12-16","cited_by_count":2,"area":null},{"id":"2312.12723","title":"Multi-Clue Reasoning with Memory Augmentation for Knowledge-based Visual Question Answering","created":"2023-12-20","cited_by_count":2,"area":null},{"id":"2510.06938","title":"Expressive and Scalable Quantum Fusion for Multimodal Learning","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2305.19871","title":"There is more to graphs than meets the eye: Learning universal features with self-supervision","created":"2023-05-31","cited_by_count":1,"area":null},{"id":"2403.07518","title":"Open-Vocabulary Scene Text Recognition via Pseudo-Image Labeling and Margin Loss","created":"2024-03-12","cited_by_count":0,"area":null},{"id":"2407.07639","title":"Explaining Graph Neural Networks for Node Similarity on Graphs","created":"2024-07-10","cited_by_count":0,"area":null},{"id":"2505.19554","title":"Aggregated Structural Representation with Large Language Models for Human-Centric Layout Generation","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2601.13919","title":"HyperWalker: Dynamic Hypergraph-Based Deep Diagnosis for Multi-Hop Clinical Modeling across EHR and X-Ray in Medical VLMs","created":"2026-01-20","cited_by_count":0,"area":null}],"next_cursor":null}