{"total":62,"rows":[{"id":"2203.09517","title":"TensoRF: Tensorial Radiance Fields","created":"2022-03-17","cited_by_count":1280,"area":null},{"id":"2101.05307","title":"Explainability of deep vision-based autonomous driving systems: Review and challenges","created":"2021-01-13","cited_by_count":80,"area":null},{"id":"2201.00443","title":"Scene Graph Generation: A Comprehensive Survey","created":"2022-01-03","cited_by_count":73,"area":null},{"id":"2104.03149","title":"Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question Answering","created":"2021-04-07","cited_by_count":71,"area":null},{"id":"2206.02349","title":"Invariant Grounding for Video Question Answering","created":"2022-06-06","cited_by_count":68,"area":null},{"id":"2101.05544","title":"DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation","created":"2021-01-14","cited_by_count":48,"area":null},{"id":"2304.09974","title":"SurgicalGPT: End-to-End Language-Vision GPT for Visual Question Answering in Surgery","created":"2023-04-19","cited_by_count":48,"area":null},{"id":"2106.10815","title":"Structured Sparse R-CNN for Direct Scene Graph Generation","created":"2021-06-21","cited_by_count":44,"area":null},{"id":"2103.14470","title":"Spatial Dual-Modality Graph Reasoning for Key Information Extraction","created":"2021-03-26","cited_by_count":43,"area":null},{"id":"2401.01505","title":"Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports","created":"2024-01-03","cited_by_count":41,"area":null},{"id":"2405.10948","title":"Surgical-LVLM: Learning to Adapt Large Vision-Language Model for Grounded Visual Question Answering in Robotic Surgery","created":"2024-03-22","cited_by_count":39,"area":"mllm"},{"id":"2501.11347","title":"EndoChat: Grounded Multimodal Large Language Model for Endoscopic Surgery","created":"2025-01-20","cited_by_count":37,"area":"mllm"},{"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":"2103.05568","title":"Select, Substitute, Search: A New Benchmark for Knowledge-Augmented Visual Question Answering","created":"2021-03-09","cited_by_count":33,"area":null},{"id":"2306.09328","title":"WizMap: Scalable Interactive Visualization for Exploring Large Machine Learning Embeddings","created":"2023-06-15","cited_by_count":28,"area":null},{"id":"2104.03015","title":"RTIC: Residual Learning for Text and Image Composition using Graph Convolutional Network","created":"2021-04-07","cited_by_count":27,"area":null},{"id":"2302.10909","title":"Multi-modal Machine Learning in Engineering Design: A Review and Future Directions","created":"2023-02-14","cited_by_count":27,"area":null},{"id":"2204.07780","title":"Towards Lightweight Transformer via Group-wise Transformation for Vision-and-Language Tasks","created":"2022-04-16","cited_by_count":21,"area":null},{"id":"2210.02081","title":"Locate before Answering: Answer Guided Question Localization for Video Question Answering","created":"2022-10-05","cited_by_count":19,"area":null},{"id":"2207.11850","title":"Visual Perturbation-aware Collaborative Learning for Overcoming the Language Prior Problem","created":"2022-07-24","cited_by_count":18,"area":null},{"id":"2105.14300","title":"LPF: A Language-Prior Feedback Objective Function for De-biased Visual Question Answering","created":"2021-05-29","cited_by_count":17,"area":null},{"id":"2307.05182","title":"CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery","created":"2023-07-11","cited_by_count":17,"area":null},{"id":"2408.04958","title":"Surgical-VQLA++: Adversarial Contrastive Learning for Calibrated Robust Visual Question-Localized Answering in Robotic Surgery","created":"2024-08-09","cited_by_count":17,"area":null},{"id":"2504.14692","title":"OmniV-Med: Scaling Medical Vision-Language Model for Universal Visual Understanding","created":"2025-04-20","cited_by_count":17,"area":"mllm"},{"id":"2107.12604","title":"Image Scene Graph Generation (SGG) Benchmark","created":"2021-07-27","cited_by_count":15,"area":null},{"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":"2105.00421","title":"A survey on VQA_Datasets and Approaches","created":"2021-05-02","cited_by_count":11,"area":null},{"id":"2406.02038","title":"Leveraging Predicate and Triplet Learning for Scene Graph Generation","created":"2024-06-04","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":"2209.06954","title":"Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering","created":"2022-09-14","cited_by_count":7,"area":"mllm"},{"id":"2109.11848","title":"How to find a good image-text embedding for remote sensing visual question answering?","created":"2021-09-24","cited_by_count":6,"area":null},{"id":"2311.04192","title":"JaSPICE: Automatic Evaluation Metric Using Predicate-Argument Structures for Image Captioning Models","created":"2023-11-07","cited_by_count":6,"area":null},{"id":"2411.10937","title":"Memory-Augmented Multimodal LLMs for Surgical VQA via Self-Contained Inquiry","created":"2024-11-17","cited_by_count":6,"area":"mllm"},{"id":"2207.10404","title":"Semantic-aware Modular Capsule Routing for Visual Question Answering","created":"2022-07-21","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":"2302.05894","title":"Neural Architecture Search with Multimodal Fusion Methods for Diagnosing Dementia","created":"2023-02-12","cited_by_count":4,"area":null},{"id":"2309.11718","title":"CPR-Coach: Recognizing Composite Error Actions based on Single-class Training","created":"2023-09-21","cited_by_count":4,"area":null},{"id":"2410.15266","title":"GSSF: Generalized Structural Sparse Function for Deep Cross-modal Metric Learning","created":"2024-10-20","cited_by_count":4,"area":null},{"id":"2411.10684","title":"HIST-AID: Leveraging Historical Patient Reports for Enhanced Multi-Modal Automatic Diagnosis","created":"2024-11-16","cited_by_count":4,"area":null},{"id":"2206.12533","title":"From Shallow to Deep: Compositional Reasoning over Graphs for Visual Question Answering","created":"2022-06-25","cited_by_count":3,"area":null},{"id":"2307.14142","title":"LOIS: Looking Out of Instance Semantics for Visual Question Answering","created":"2023-07-26","cited_by_count":3,"area":null},{"id":"2201.10656","title":"MGA-VQA: Multi-Granularity Alignment for Visual Question Answering","created":"2022-01-25","cited_by_count":2,"area":null},{"id":"2205.04402","title":"Detecting the Role of an Entity in Harmful Memes: Techniques and Their Limitations","created":"2022-05-09","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":"2212.10632","title":"High-Throughput, High-Performance Deep Learning-Driven Light Guide Plate Surface Visual Quality Inspection Tailored for Real-World Manufacturing Environments","created":"2022-12-20","cited_by_count":2,"area":null},{"id":"2301.07526","title":"AutoFraudNet: A Multimodal Network to Detect Fraud in the Auto Insurance Industry","created":"2023-01-15","cited_by_count":2,"area":null},{"id":"2309.03542","title":"Zero-Shot Scene Graph Generation via Triplet Calibration and Reduction","created":"2023-09-07","cited_by_count":2,"area":null},{"id":"2309.04734","title":"Towards Better Multi-modal Keyphrase Generation via Visual Entity Enhancement and Multi-granularity Image Noise Filtering","created":"2023-09-09","cited_by_count":2,"area":null},{"id":"2401.09442","title":"Object Attribute Matters in Visual Question Answering","created":"2023-12-20","cited_by_count":2,"area":"distill"},{"id":"2407.00056","title":"MMBee: Live Streaming Gift-Sending Recommendations via Multi-Modal Fusion and Behaviour Expansion","created":"2024-06-15","cited_by_count":2,"area":null},{"id":"2202.06858","title":"An experimental study of the vision-bottleneck in VQA","created":"2022-02-14","cited_by_count":1,"area":null},{"id":"2205.04404","title":"TeamX@DravidianLangTech-ACL2022: A Comparative Analysis for Troll-Based Meme Classification","created":"2022-05-09","cited_by_count":1,"area":null},{"id":"2212.03370","title":"Probabilistic Shape Completion by Estimating Canonical Factors with Hierarchical VAE","created":"2022-12-06","cited_by_count":1,"area":null},{"id":"2502.20213","title":"Mixture of Experts for Recognizing Depression from Interview and Reading Tasks","created":"2025-02-27","cited_by_count":1,"area":"moe"},{"id":"2201.10654","title":"SA-VQA: Structured Alignment of Visual and Semantic Representations for Visual Question Answering","created":"2022-01-25","cited_by_count":0,"area":null},{"id":"2206.09111","title":"VReBERT: A Simple and Flexible Transformer for Visual Relationship Detection","created":"2022-06-18","cited_by_count":0,"area":null},{"id":"2211.11190","title":"Cross-Modal Contrastive Learning for Robust Reasoning in VQA","created":"2022-11-21","cited_by_count":0,"area":null},{"id":"2302.14777","title":"VQA with Cascade of Self- and Co-Attention Blocks","created":"2023-02-28","cited_by_count":0,"area":null},{"id":"2310.05410","title":"Causal Reasoning through Two Layers of Cognition for Improving Generalization in Visual Question Answering","created":"2023-10-09","cited_by_count":0,"area":"lr"},{"id":"2403.00724","title":"Few-Shot Relation Extraction with Hybrid Visual Evidence","created":"2024-03-01","cited_by_count":0,"area":null},{"id":"2605.25540","title":"A Multimodal Framework for Dementia Detection via Linguistic and Acoustic Representation Learning","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2607.22709","title":"RMS@CC-MMD 2026: Multimodal Misogyny Detection via Geometric Interaction and Multi-View Consensus","created":"2026-07-20","cited_by_count":0,"area":null}],"next_cursor":null}