{"total":278,"rows":[{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744,"area":null},{"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":"2406.01171","title":"Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization","created":"2024-06-03","cited_by_count":208,"area":null},{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191,"area":null},{"id":"2104.03135","title":"Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning","created":"2021-04-07","cited_by_count":187,"area":"mllm"},{"id":"2210.06044","title":"Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning","created":"2022-10-12","cited_by_count":159,"area":null},{"id":"2103.16002","title":"AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning","created":"2021-03-30","cited_by_count":120,"area":null},{"id":"2108.08728","title":"Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification","created":"2021-08-19","cited_by_count":114,"area":null},{"id":"2103.03493","title":"Causal Attention for Vision-Language Tasks","created":"2021-03-05","cited_by_count":111,"area":"mllm"},{"id":"2106.09141","title":"Probing Image-Language Transformers for Verb Understanding","created":"2021-06-16","cited_by_count":109,"area":null},{"id":"2106.09707","title":"Learning to Predict Visual Attributes in the Wild","created":"2021-06-17","cited_by_count":96,"area":null},{"id":"2111.10056","title":"Medical Visual Question Answering: A Survey","created":"2021-11-19","cited_by_count":93,"area":null},{"id":"2108.02388","title":"TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding","created":"2021-08-05","cited_by_count":86,"area":null},{"id":"2203.01225","title":"Video Question Answering: Datasets, Algorithms and Challenges","created":"2022-03-02","cited_by_count":84,"area":null},{"id":"2203.08101","title":"ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity","created":"2022-03-15","cited_by_count":83,"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":"2103.12248","title":"Multi-Modal Answer Validation for Knowledge-Based VQA","created":"2021-03-23","cited_by_count":79,"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":"2106.07876","title":"Vision-Language Navigation with Random Environmental Mixup","created":"2021-06-15","cited_by_count":70,"area":null},{"id":"2308.01399","title":"Learning to Model the World with Language","created":"2023-07-31","cited_by_count":68,"area":null},{"id":"2303.07284","title":"Align and Attend: Multimodal Summarization with Dual Contrastive Losses","created":"2023-03-13","cited_by_count":65,"area":null},{"id":"2102.00529","title":"Decoupling the Role of Data, Attention, and Losses in Multimodal Transformers","created":"2021-01-31","cited_by_count":64,"area":null},{"id":"2203.14263","title":"A General Survey on Attention Mechanisms in Deep Learning","created":"2022-03-27","cited_by_count":64,"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":"2403.04640","title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2024-03-07","cited_by_count":53,"area":"mllm"},{"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":"2306.09486","title":"FedMultimodal: A Benchmark For Multimodal Federated Learning","created":"2023-06-15","cited_by_count":51,"area":null},{"id":"2104.06387","title":"ExplainaBoard: An Explainable Leaderboard for NLP","created":"2021-04-13","cited_by_count":50,"area":null},{"id":"2204.07548","title":"Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation","created":"2022-04-15","cited_by_count":47,"area":null},{"id":"2202.06511","title":"GAMMA Challenge:Glaucoma grAding from Multi-Modality imAges","created":"2022-02-14","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":"2101.12059","title":"VX2TEXT: End-to-End Learning of Video-Based Text Generation From Multimodal Inputs","created":"2021-01-28","cited_by_count":42,"area":null},{"id":"2109.06398","title":"Adaptive Proposal Generation Network for Temporal Sentence Localization in Videos","created":"2021-09-14","cited_by_count":42,"area":null},{"id":"2112.08359","title":"3D Question Answering","created":"2021-12-15","cited_by_count":41,"area":null},{"id":"2210.14530","title":"RGB-T Semantic Segmentation with Location, Activation, and Sharpening","created":"2022-10-26","cited_by_count":39,"area":null},{"id":"2107.05348","title":"Zero-shot Visual Question Answering using Knowledge Graph","created":"2021-07-12","cited_by_count":37,"area":null},{"id":"2112.07668","title":"Dual-Key Multimodal Backdoors for Visual Question Answering","created":"2021-12-14","cited_by_count":37,"area":"safety"},{"id":"2103.16561","title":"Diagnosing Vision-and-Language Navigation: What Really Matters","created":"2021-03-30","cited_by_count":36,"area":null},{"id":"2107.13782","title":"Multimodal Co-learning: Challenges, Applications with Datasets, Recent Advances and Future Directions","created":"2021-07-29","cited_by_count":35,"area":null},{"id":"2203.02966","title":"Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding","created":"2022-03-06","cited_by_count":35,"area":null},{"id":"2110.08515","title":"Multimodal Dialogue Response Generation","created":"2021-10-16","cited_by_count":32,"area":null},{"id":"2312.03543","title":"GPT-4 Enhanced Multimodal Grounding for Autonomous Driving: Leveraging Cross-Modal Attention with Large Language Models","created":"2023-12-06","cited_by_count":32,"area":"driving"},{"id":"2103.11072","title":"Local Interpretations for Explainable Natural Language Processing: A Survey","created":"2021-03-20","cited_by_count":31,"area":null},{"id":"2109.06400","title":"Progressively Guide to Attend: An Iterative Alignment Framework for Temporal Sentence Grounding","created":"2021-09-14","cited_by_count":31,"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":"2205.05019","title":"Learning to Answer Visual Questions from Web Videos","created":"2022-05-10","cited_by_count":30,"area":null},{"id":"2109.01876","title":"Attentive Neural Controlled Differential Equations for Time-series Classification and Forecasting","created":"2021-09-04","cited_by_count":29,"area":null},{"id":"2204.13154","title":"Attention Mechanism in Neural Networks: Where it Comes and Where it Goes","created":"2022-04-27","cited_by_count":29,"area":null},{"id":"2308.05421","title":"Progressive Spatio-temporal Perception for Audio-Visual Question Answering","created":"2023-08-10","cited_by_count":29,"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":"2207.00938","title":"Interpretable by Design: Learning Predictors by Composing Interpretable Queries","created":"2022-07-03","cited_by_count":28,"area":null},{"id":"2207.12622","title":"Multi-Attention Network for Compressed Video Referring Object Segmentation","created":"2022-07-26","cited_by_count":28,"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":"2209.12028","title":"Towards Explainable 3D Grounded Visual Question Answering: A New Benchmark and Strong Baseline","created":"2022-09-24","cited_by_count":25,"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":"2201.00457","title":"Exploring Motion and Appearance Information for Temporal Sentence Grounding","created":"2022-01-03","cited_by_count":24,"area":null},{"id":"2402.02045","title":"MLIP: Enhancing Medical Visual Representation with Divergence Encoder and Knowledge-guided Contrastive Learning","created":"2024-02-03","cited_by_count":23,"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":"2103.10702","title":"ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation","created":"2021-03-19","cited_by_count":21,"area":null},{"id":"2110.00804","title":"ProTo: Program-Guided Transformer for Program-Guided Tasks","created":"2021-10-02","cited_by_count":21,"area":null},{"id":"2111.13517","title":"Not All Relations are Equal: Mining Informative Labels for Scene Graph Generation","created":"2021-11-26","cited_by_count":21,"area":null},{"id":"2207.13450","title":"Skimming, Locating, then Perusing: A Human-Like Framework for Natural Language Video Localization","created":"2022-07-27","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":"2109.13139","title":"Multimodal Integration of Human-Like Attention in Visual Question Answering","created":"2021-09-27","cited_by_count":20,"area":null},{"id":"2305.04183","title":"OpenViVQA: Task, Dataset, and Multimodal Fusion Models for Visual Question Answering in Vietnamese","created":"2023-05-07","cited_by_count":20,"area":null},{"id":"2104.00926","title":"VisQA: X-raying Vision and Language Reasoning in Transformers","created":"2021-04-02","cited_by_count":19,"area":null},{"id":"2108.10696","title":"Spatio-Temporal Self-Attention Network for Video Saliency Prediction","created":"2021-08-24","cited_by_count":19,"area":null},{"id":"2109.06980","title":"Explainable Identification of Dementia from Transcripts using Transformer Networks","created":"2021-09-14","cited_by_count":19,"area":null},{"id":"2303.13043","title":"Top-Down Visual Attention from Analysis by Synthesis","created":"2023-03-23","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":"2203.14266","title":"A Survey on Aspect-Based Sentiment Classification","created":"2022-03-27","cited_by_count":18,"area":null},{"id":"2206.14989","title":"A Unified End-to-End Retriever-Reader Framework for Knowledge-based VQA","created":"2022-06-30","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":"2212.00715","title":"What do you MEME? Generating Explanations for Visual Semantic Role Labelling in Memes","created":"2022-12-01","cited_by_count":18,"area":null},{"id":"2404.12020","title":"Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering","created":"2024-04-18","cited_by_count":18,"area":null},{"id":"2102.07751","title":"Deep Co-Attention Network for Multi-View Subspace Learning","created":"2021-02-15","cited_by_count":17,"area":null},{"id":"2307.13214","title":"FedMEKT: Distillation-based Embedding Knowledge Transfer for Multimodal Federated Learning","created":"2023-07-25","cited_by_count":17,"area":null},{"id":"2102.11903","title":"Neural ranking models for document retrieval","created":"2021-02-23","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":"2110.06058","title":"Multi-Modal Interaction Graph Convolutional Network for Temporal Language Localization in Videos","created":"2021-10-12","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":"2206.02082","title":"Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval","created":"2022-06-05","cited_by_count":16,"area":null},{"id":"2301.02778","title":"Lightweight Salient Object Detection in Optical Remote-Sensing Images via Semantic Matching and Edge Alignment","created":"2023-01-07","cited_by_count":16,"area":null},{"id":"2305.18842","title":"Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge","created":"2023-05-30","cited_by_count":16,"area":null},{"id":"2105.14953","title":"ACE-NODE: Attentive Co-Evolving Neural Ordinary Differential Equations","created":"2021-05-31","cited_by_count":15,"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":"2201.08049","title":"Lightweight Salient Object Detection in Optical Remote Sensing Images via Feature Correlation","created":"2022-01-20","cited_by_count":15,"area":null},{"id":"2309.02224","title":"Dense Object Grounding in 3D Scenes","created":"2023-09-05","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":"2205.07548","title":"A Neuro-Symbolic ASP Pipeline for Visual Question Answering","created":"2022-05-16","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":"2407.20693","title":"Boosting Audio Visual Question Answering via Key Semantic-Aware Cues","created":"2024-07-30","cited_by_count":14,"area":null},{"id":"2104.09379","title":"BM-NAS: Bilevel Multimodal Neural Architecture Search","created":"2021-04-19","cited_by_count":13,"area":null},{"id":"2106.11229","title":"AOMD: An Analogy-aware Approach to Offensive Meme Detection on Social Media","created":"2021-06-21","cited_by_count":13,"area":null},{"id":"2109.08475","title":"GoG: Relation-aware Graph-over-Graph Network for Visual Dialog","created":"2021-09-17","cited_by_count":13,"area":null},{"id":"2205.04188","title":"Joint learning of object graph and relation graph for visual question answering","created":"2022-05-09","cited_by_count":13,"area":null}],"next_cursor":"100"}