{"total":243,"rows":[{"id":"2112.12143","title":"Scaling Open-Vocabulary Image Segmentation with Image-Level Labels","created":"2021-12-22","cited_by_count":473,"area":null},{"id":"2107.06383","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","created":"2021-07-13","cited_by_count":321,"area":null},{"id":"2211.08332","title":"Versatile Diffusion: Text, Images and Variations All in One Diffusion Model","created":"2022-11-15","cited_by_count":199,"area":"diffusion"},{"id":"2312.16217","title":"ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation","created":"2023-12-24","cited_by_count":162,"area":"lr"},{"id":"2101.06894","title":"Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs","created":"2021-01-18","cited_by_count":144,"area":null},{"id":"2112.08879","title":"Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds","created":"2021-12-16","cited_by_count":128,"area":null},{"id":"2210.12634","title":"RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data","created":"2022-10-23","cited_by_count":123,"area":null},{"id":"2208.05358","title":"CLEVR-Math: A Dataset for Compositional Language, Visual and Mathematical Reasoning","created":"2022-08-10","cited_by_count":120,"area":"lr"},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2408.06327","title":"VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents","created":"2024-08-12","cited_by_count":103,"area":"mllm"},{"id":"2207.08954","title":"Exploiting Unlabeled Data with Vision and Language Models for Object Detection","created":"2022-07-18","cited_by_count":97,"area":null},{"id":"2111.10056","title":"Medical Visual Question Answering: A Survey","created":"2021-11-19","cited_by_count":93,"area":null},{"id":"2212.00259","title":"Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoning","created":"2022-12-01","cited_by_count":92,"area":"lr"},{"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":"2505.04921","title":"Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models","created":"2025-05-08","cited_by_count":90,"area":"lr"},{"id":"2204.13631","title":"Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly","created":"2022-04-28","cited_by_count":89,"area":null},{"id":"2105.03761","title":"e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks","created":"2021-05-08","cited_by_count":84,"area":null},{"id":"2302.12247","title":"Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework","created":"2023-02-23","cited_by_count":83,"area":null},{"id":"2202.02703","title":"Multi-modal Sensor Fusion for Auto Driving Perception: A Survey","created":"2022-02-06","cited_by_count":76,"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":"2103.03433","title":"Goal-Oriented Gaze Estimation for Zero-Shot Learning","created":"2021-03-05","cited_by_count":68,"area":null},{"id":"2107.02331","title":"Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering","created":"2021-07-06","cited_by_count":62,"area":null},{"id":"2203.05081","title":"NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks","created":"2022-03-09","cited_by_count":60,"area":null},{"id":"2106.02280","title":"Human-Adversarial Visual Question Answering","created":"2021-06-04","cited_by_count":57,"area":null},{"id":"2210.05916","title":"Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Features","created":"2022-10-12","cited_by_count":56,"area":null},{"id":"2105.08913","title":"Multiple Meta-model Quantifying for Medical Visual Question Answering","created":"2021-05-19","cited_by_count":54,"area":null},{"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":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2207.01076","title":"Divert More Attention to Vision-Language Tracking","created":"2022-07-03","cited_by_count":47,"area":null},{"id":"2102.05281","title":"Biomedical Question Answering: A Survey of Approaches and Challenges","created":"2021-02-10","cited_by_count":46,"area":null},{"id":"2105.07878","title":"A Review on Explainability in Multimodal Deep Neural Nets","created":"2021-05-17","cited_by_count":46,"area":null},{"id":"2108.09322","title":"MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition","created":"2021-08-20","cited_by_count":46,"area":null},{"id":"2404.13565","title":"Exploring Diverse Methods in Visual Question Answering","created":"2024-04-21","cited_by_count":45,"area":null},{"id":"2106.02192","title":"Grounding 'Grounding' in NLP","created":"2021-06-04","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":"2201.12944","title":"Deep Learning Approaches on Image Captioning: A Review","created":"2022-01-31","cited_by_count":43,"area":"mllm"},{"id":"2105.04281","title":"Visual Grounding with Transformers","created":"2021-05-10","cited_by_count":42,"area":null},{"id":"2209.04355","title":"MIntRec: A New Dataset for Multimodal Intent Recognition","created":"2022-09-09","cited_by_count":41,"area":null},{"id":"2312.02896","title":"BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models","created":"2023-12-05","cited_by_count":41,"area":"lr"},{"id":"2205.03147","title":"From Easy to Hard: Learning Language-guided Curriculum for Visual Question Answering on Remote Sensing Data","created":"2022-05-06","cited_by_count":39,"area":null},{"id":"2204.02285","title":"SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering","created":"2022-04-05","cited_by_count":38,"area":null},{"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":"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":"2301.11843","title":"Reading and Reasoning over Chart Images for Evidence-based Automated Fact-Checking","created":"2023-01-27","cited_by_count":35,"area":null},{"id":"2302.09019","title":"Tensor Networks Meet Neural Networks: A Survey and Future Perspectives","created":"2023-01-22","cited_by_count":32,"area":null},{"id":"2205.05019","title":"Learning to Answer Visual Questions from Web Videos","created":"2022-05-10","cited_by_count":30,"area":null},{"id":"2401.05698","title":"HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition","created":"2024-01-11","cited_by_count":30,"area":null},{"id":"2104.03236","title":"Multimodal Entity Linking for Tweets","created":"2021-04-07","cited_by_count":28,"area":null},{"id":"2112.00974","title":"Consensus Graph Representation Learning for Better Grounded Image Captioning","created":"2021-12-02","cited_by_count":28,"area":null},{"id":"2203.01922","title":"Vision-Language Intelligence: Tasks, Representation Learning, and Large Models","created":"2022-03-03","cited_by_count":28,"area":null},{"id":"2506.01949","title":"IMAGHarmony: Controllable Image Editing with Consistent Object Quantity and Layout","created":"2025-06-02","cited_by_count":28,"area":"diffusion"},{"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":"2210.03416","title":"Detailed Annotations of Chest X-Rays via CT Projection for Report Understanding","created":"2022-10-07","cited_by_count":26,"area":null},{"id":"2403.10943","title":"MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations","created":"2024-03-16","cited_by_count":26,"area":null},{"id":"2506.11147","title":"3D-RAD: A Comprehensive 3D Radiology Med-VQA Dataset with Multi-Temporal Analysis and Diverse Diagnostic Tasks","created":"2025-06-11","cited_by_count":26,"area":null},{"id":"2306.05731","title":"Multimodal Explainable Artificial Intelligence: A Comprehensive Review of Methodological Advances and Future Research Directions","created":"2023-06-09","cited_by_count":25,"area":null},{"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":"2502.14917","title":"Sce2DriveX: A Generalized MLLM Framework for Scene-to-Drive Learning","created":"2025-02-19","cited_by_count":25,"area":"driving"},{"id":"2211.15516","title":"DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and Grounding","created":"2022-11-28","cited_by_count":24,"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":"2110.01013","title":"Counterfactual Samples Synthesizing and Training for Robust Visual Question Answering","created":"2021-10-03","cited_by_count":22,"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":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","cited_by_count":22,"area":null},{"id":"2104.05947","title":"\"Subverting the Jewtocracy\": Online Antisemitism Detection Using Multimodal Deep Learning","created":"2021-04-13","cited_by_count":21,"area":null},{"id":"2204.03647","title":"Adapting CLIP For Phrase Localization Without Further Training","created":"2022-04-07","cited_by_count":21,"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":"2301.09460","title":"HRVQA: A Visual Question Answering Benchmark for High-Resolution Aerial Images","created":"2023-01-23","cited_by_count":21,"area":null},{"id":"2306.04539","title":"Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications","created":"2023-06-07","cited_by_count":21,"area":null},{"id":"2312.06037","title":"Multimodality of AI for Education: Towards Artificial General Intelligence","created":"2023-12-10","cited_by_count":21,"area":null},{"id":"2405.14974","title":"LOVA3: Learning to Visual Question Answering, Asking and Assessment","created":"2024-05-23","cited_by_count":21,"area":null},{"id":"2202.12690","title":"On Modality Bias Recognition and Reduction","created":"2022-02-25","cited_by_count":20,"area":null},{"id":"2205.13724","title":"V-Doc : Visual questions answers with Documents","created":"2022-05-27","cited_by_count":19,"area":null},{"id":"2409.01763","title":"FC-KAN: Function Combinations in Kolmogorov-Arnold Networks","created":"2024-09-03","cited_by_count":19,"area":null},{"id":"2105.01993","title":"AdaVQA: Overcoming Language Priors with Adapted Margin Cosine Loss","created":"2021-05-05","cited_by_count":18,"area":null},{"id":"2108.05863","title":"Towers of Babel: Combining Images, Language, and 3D Geometry for Learning Multimodal Vision","created":"2021-08-12","cited_by_count":18,"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":"2104.06008","title":"Disentangled Motif-aware Graph Learning for Phrase Grounding","created":"2021-04-13","cited_by_count":17,"area":null},{"id":"2112.11691","title":"Comprehensive Visual Question Answering on Point Clouds through Compositional Scene Manipulation","created":"2021-12-22","cited_by_count":17,"area":null},{"id":"2211.07912","title":"YORO -- Lightweight End to End Visual Grounding","created":"2022-11-15","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":"2108.07253","title":"Who's Waldo? Linking People Across Text and Images","created":"2021-08-16","cited_by_count":16,"area":null},{"id":"2204.02380","title":"CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations","created":"2022-04-05","cited_by_count":16,"area":"lr"},{"id":"2310.17914","title":"3D-Aware Visual Question Answering about Parts, Poses and Occlusions","created":"2023-10-27","cited_by_count":16,"area":null},{"id":"2106.04484","title":"Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions","created":"2021-06-08","cited_by_count":15,"area":null},{"id":"2106.10548","title":"VQA-Aid: Visual Question Answering for Post-Disaster Damage Assessment and Analysis","created":"2021-06-19","cited_by_count":15,"area":null},{"id":"2110.06688","title":"DeepVecFont: Synthesizing High-quality Vector Fonts via Dual-modality Learning","created":"2021-10-13","cited_by_count":15,"area":null},{"id":"2305.02519","title":"ANetQA: A Large-scale Benchmark for Fine-grained Compositional Reasoning over Untrimmed Videos","created":"2023-05-04","cited_by_count":15,"area":null},{"id":"2503.06973","title":"A Multimodal Benchmark Dataset and Model for Crop Disease Diagnosis","created":"2025-03-10","cited_by_count":15,"area":null},{"id":"2103.04037","title":"Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Vision","created":"2021-03-06","cited_by_count":14,"area":null},{"id":"2104.05965","title":"Dealing with Missing Modalities in the Visual Question Answer-Difference Prediction Task through Knowledge Distillation","created":"2021-04-13","cited_by_count":14,"area":"distill"},{"id":"2105.02626","title":"A First Look: Towards Explainable TextVQA Models via Visual and Textual Explanations","created":"2021-04-29","cited_by_count":14,"area":null},{"id":"2110.00519","title":"Calibrating Concepts and Operations: Towards Symbolic Reasoning on Real Images","created":"2021-10-01","cited_by_count":14,"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":"2109.04653","title":"Towards Developing a Multilingual and Code-Mixed Visual Question Answering System by Knowledge Distillation","created":"2021-09-10","cited_by_count":13,"area":"distill"},{"id":"2209.01416","title":"MMKGR: Multi-hop Multi-modal Knowledge Graph Reasoning","created":"2022-09-03","cited_by_count":13,"area":"lr"},{"id":"2303.06129","title":"Single-branch Network for Multimodal Training","created":"2023-03-10","cited_by_count":13,"area":null},{"id":"2112.00967","title":"Relational Graph Learning for Grounded Video Description Generation","created":"2021-12-02","cited_by_count":12,"area":null},{"id":"2201.08712","title":"Improved Random Features for Dot Product Kernels","created":"2022-01-21","cited_by_count":12,"area":null},{"id":"2203.06107","title":"REX: Reasoning-aware and Grounded Explanation","created":"2022-03-11","cited_by_count":12,"area":null}],"next_cursor":"100"}