{"total":51,"rows":[{"id":"2305.14836","title":"NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario","created":"2023-05-24","cited_by_count":262,"area":null},{"id":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117,"area":"mllm"},{"id":"2304.06819","title":"Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction","created":"2023-04-13","cited_by_count":92,"area":null},{"id":"2209.08290","title":"Changer: Feature Interaction is What You Need for Change Detection","created":"2022-09-17","cited_by_count":79,"area":null},{"id":"2411.17558","title":"Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey","created":"2024-11-26","cited_by_count":76,"area":"mllm"},{"id":"2203.15442","title":"Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Grounding","created":"2022-03-29","cited_by_count":53,"area":"lr"},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2111.14745","title":"A Simple Long-Tailed Recognition Baseline via Vision-Language Model","created":"2021-11-29","cited_by_count":49,"area":"mllm"},{"id":"2204.07756","title":"Visual Attention Methods in Deep Learning: An In-Depth Survey","created":"2022-04-16","cited_by_count":37,"area":null},{"id":"2203.09138","title":"MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-based Visual Question Answering","created":"2022-03-17","cited_by_count":36,"area":null},{"id":"2107.04768","title":"DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering","created":"2021-07-10","cited_by_count":35,"area":null},{"id":"2312.06352","title":"NuScenes-MQA: Integrated Evaluation of Captions and QA for Autonomous Driving Datasets using Markup Annotations","created":"2023-12-11","cited_by_count":31,"area":"driving"},{"id":"2508.17298","title":"Explain Before You Answer: A Survey on Compositional Visual Reasoning","created":"2025-08-24","cited_by_count":28,"area":"lr"},{"id":"2302.00389","title":"Multimodality Representation Learning: A Survey on Evolution, Pretraining and Its Applications","created":"2023-02-01","cited_by_count":27,"area":"lr"},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2305.10822","title":"When Search Meets Recommendation: Learning Disentangled Search Representation for Recommendation","created":"2023-05-18","cited_by_count":17,"area":null},{"id":"2108.10568","title":"Auto-Parsing Network for Image Captioning and Visual Question Answering","created":"2021-08-24","cited_by_count":16,"area":null},{"id":"2109.13116","title":"VQA-MHUG: A Gaze Dataset to Study Multimodal Neural Attention in Visual Question Answering","created":"2021-09-27","cited_by_count":16,"area":null},{"id":"2202.08557","title":"CADRE: A Cascade Deep Reinforcement Learning Framework for Vision-based Autonomous Urban Driving","created":"2022-02-17","cited_by_count":16,"area":"driving"},{"id":"2212.13296","title":"VQA and Visual Reasoning: An Overview of Recent Datasets, Methods and Challenges","created":"2022-12-26","cited_by_count":14,"area":"lr"},{"id":"2209.01416","title":"MMKGR: Multi-hop Multi-modal Knowledge Graph Reasoning","created":"2022-09-03","cited_by_count":13,"area":"lr"},{"id":"2103.12346","title":"Co-Grounding Networks with Semantic Attention for Referring Expression Comprehension in Videos","created":"2021-03-23","cited_by_count":11,"area":null},{"id":"2108.02352","title":"Understand me, if you refer to Aspect Knowledge: Knowledge-aware Gated Recurrent Memory Network","created":"2021-08-05","cited_by_count":11,"area":null},{"id":"2206.01017","title":"Structured Two-stream Attention Network for Video Question Answering","created":"2022-06-02","cited_by_count":9,"area":null},{"id":"2304.03910","title":"Co-attention Propagation Network for Zero-Shot Video Object Segmentation","created":"2023-04-08","cited_by_count":9,"area":null},{"id":"2204.00879","title":"Co-VQA : Answering by Interactive Sub Question Sequence","created":"2022-04-02","cited_by_count":8,"area":null},{"id":"2411.11150","title":"A Comprehensive Survey on Visual Question Answering Datasets and Algorithms","created":"2024-11-17","cited_by_count":8,"area":null},{"id":"2112.11953","title":"Text is no more Enough! A Benchmark for Profile-based Spoken Language Understanding","created":"2021-12-22","cited_by_count":7,"area":null},{"id":"2102.08065","title":"Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries","created":"2021-02-16","cited_by_count":6,"area":null},{"id":"2207.10404","title":"Semantic-aware Modular Capsule Routing for Visual Question Answering","created":"2022-07-21","cited_by_count":5,"area":null},{"id":"2210.00220","title":"A Dual-Attention Learning Network with Word and Sentence Embedding for Medical Visual Question Answering","created":"2022-10-01","cited_by_count":5,"area":null},{"id":"2211.08736","title":"AlignVE: Visual Entailment Recognition Based on Alignment Relations","created":"2022-11-16","cited_by_count":5,"area":null},{"id":"2112.07270","title":"Bilateral Cross-Modality Graph Matching Attention for Feature Fusion in Visual Question Answering","created":"2021-12-14","cited_by_count":4,"area":null},{"id":"2305.06923","title":"EAML: Ensemble Self-Attention-based Mutual Learning Network for Document Image Classification","created":"2023-05-11","cited_by_count":4,"area":null},{"id":"2112.05917","title":"Show, Write, and Retrieve: Entity-aware Article Generation and Retrieval","created":"2021-12-11","cited_by_count":3,"area":null},{"id":"2401.12439","title":"MAST: Video Polyp Segmentation with a Mixture-Attention Siamese Transformer","created":"2024-01-23","cited_by_count":3,"area":null},{"id":"2406.05668","title":"SRC-Net: Bi-Temporal Spatial Relationship Concerned Network for Change Detection","created":"2024-06-09","cited_by_count":3,"area":null},{"id":"2101.08978","title":"Visual Question Answering based on Local-Scene-Aware Referring Expression Generation","created":"2021-01-22","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":"2312.09525","title":"Hierarchical Graph Pattern Understanding for Zero-Shot VOS","created":"2023-12-15","cited_by_count":2,"area":null},{"id":"2108.05308","title":"A Better Loss for Visual-Textual Grounding","created":"2021-08-11","cited_by_count":1,"area":null},{"id":"2203.12814","title":"Bilaterally Slimmable Transformer for Elastic and Efficient Visual Question Answering","created":"2022-03-24","cited_by_count":1,"area":null},{"id":"2206.12101","title":"Do You Know My Emotion? Emotion-Aware Strategy Recognition towards a Persuasive Dialogue System","created":"2022-06-24","cited_by_count":1,"area":null},{"id":"2309.09179","title":"Syntax Tree Constrained Graph Network for Visual Question Answering","created":"2023-09-17","cited_by_count":1,"area":null},{"id":"2309.09482","title":"Spatio-temporal Co-attention Fusion Network for Video Splicing Localization","created":"2023-09-18","cited_by_count":1,"area":null},{"id":"2102.00441","title":"M2FN: Multi-step Modality Fusion for Advertisement Image Assessment","created":"2021-01-31","cited_by_count":0,"area":null},{"id":"2110.06416","title":"MMIU: Dataset for Visual Intent Understanding in Multimodal Assistants","created":"2021-10-13","cited_by_count":0,"area":null},{"id":"2210.02445","title":"Localizing Anatomical Landmarks in Ocular Images using Zoom-In Attentive Networks","created":"2022-09-25","cited_by_count":0,"area":null},{"id":"2301.01955","title":"Adaptively Clustering Neighbor Elements for Image-Text Generation","created":"2023-01-05","cited_by_count":0,"area":null},{"id":"2302.09208","title":"Bridge Damage Cause Estimation Using Multiple Images Based on Visual Question Answering","created":"2023-02-18","cited_by_count":0,"area":null},{"id":"2305.19924","title":"Joint Adaptive Representations for Image-Language Learning","created":"2023-05-31","cited_by_count":0,"area":null}],"next_cursor":null}