{"total":139,"rows":[{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230,"area":null},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819,"area":null},{"id":"2203.00680","title":"CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding","created":"2022-03-01","cited_by_count":198,"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":"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":"2112.00826","title":"Inducing Causal Structure for Interpretable Neural Networks","created":"2021-12-01","cited_by_count":110,"area":null},{"id":"2101.03737","title":"Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals","created":"2021-01-11","cited_by_count":101,"area":null},{"id":"2101.12609","title":"Open World Compositional Zero-Shot Learning","created":"2021-01-29","cited_by_count":101,"area":null},{"id":"2212.10015","title":"Benchmarking Spatial Relationships in Text-to-Image Generation","created":"2022-12-20","cited_by_count":97,"area":null},{"id":"2103.15538","title":"SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events","created":"2021-03-29","cited_by_count":84,"area":null},{"id":"2103.16564","title":"Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning","created":"2021-03-30","cited_by_count":68,"area":null},{"id":"2205.01089","title":"ComPhy: Compositional Physical Reasoning of Objects and Events from Videos","created":"2022-05-02","cited_by_count":63,"area":null},{"id":"2110.15358","title":"Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language","created":"2021-10-28","cited_by_count":55,"area":null},{"id":"2312.12222","title":"EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering","created":"2023-12-19","cited_by_count":52,"area":null},{"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":"2207.00429","title":"Modular Lifelong Reinforcement Learning via Neural Composition","created":"2022-07-01","cited_by_count":40,"area":null},{"id":"2111.08164","title":"A Survey on Neural-symbolic Learning Systems","created":"2021-11-10","cited_by_count":39,"area":null},{"id":"2210.15889","title":"Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing","created":"2022-10-28","cited_by_count":35,"area":null},{"id":"2112.05136","title":"PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning","created":"2021-12-09","cited_by_count":34,"area":null},{"id":"2103.09591","title":"Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQA","created":"2021-03-17","cited_by_count":30,"area":null},{"id":"2310.07160","title":"LLark: A Multimodal Instruction-Following Language Model for Music","created":"2023-10-11","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":"2206.05056","title":"On Neural Architecture Inductive Biases for Relational Tasks","created":"2022-06-09","cited_by_count":26,"area":null},{"id":"2109.10613","title":"COVR: A test-bed for Visually Grounded Compositional Generalization with real images","created":"2021-09-22","cited_by_count":25,"area":null},{"id":"2107.09106","title":"Separating Skills and Concepts for Novel Visual Question Answering","created":"2021-07-19","cited_by_count":24,"area":null},{"id":"2110.06399","title":"Dynamic Inference with Neural Interpreters","created":"2021-10-12","cited_by_count":24,"area":null},{"id":"2105.04836","title":"Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsules","created":"2021-05-11","cited_by_count":22,"area":null},{"id":"2109.06133","title":"Neuro-Symbolic AI: An Emerging Class of AI Workloads and their Characterization","created":"2021-09-13","cited_by_count":22,"area":null},{"id":"2105.01119","title":"Iterated learning for emergent systematicity in VQA","created":"2021-05-03","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":"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":"2207.04136","title":"CompoSuite: A Compositional Reinforcement Learning Benchmark","created":"2022-07-08","cited_by_count":21,"area":null},{"id":"2101.05479","title":"Understanding the Role of Scene Graphs in Visual Question Answering","created":"2021-01-14","cited_by_count":20,"area":null},{"id":"2203.16639","title":"FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations","created":"2022-03-30","cited_by_count":20,"area":null},{"id":"2109.08994","title":"ReaSCAN: Compositional Reasoning in Language Grounding","created":"2021-09-18","cited_by_count":19,"area":null},{"id":"2112.05892","title":"COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality","created":"2021-12-11","cited_by_count":19,"area":null},{"id":"2205.13724","title":"V-Doc : Visual questions answers with Documents","created":"2022-05-27","cited_by_count":19,"area":null},{"id":"2301.09071","title":"Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Grounding","created":"2023-01-22","cited_by_count":19,"area":null},{"id":"2404.08589","title":"Enhancing Visual Question Answering through Question-Driven Image Captions as Prompts","created":"2024-04-12","cited_by_count":18,"area":null},{"id":"2110.08797","title":"Towards Language-guided Visual Recognition via Dynamic Convolutions","created":"2021-10-17","cited_by_count":17,"area":null},{"id":"2310.05136","title":"InstructDET: Diversifying Referring Object Detection with Generalized Instructions","created":"2023-10-08","cited_by_count":16,"area":null},{"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":"2106.08170","title":"How Modular Should Neural Module Networks Be for Systematic Generalization?","created":"2021-06-15","cited_by_count":15,"area":null},{"id":"2109.12243","title":"Systematic Generalization on gSCAN: What is Nearly Solved and What is Next?","created":"2021-09-25","cited_by_count":15,"area":null},{"id":"2204.11167","title":"RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning","created":"2022-04-24","cited_by_count":15,"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":"2107.06325","title":"Graphhopper: Multi-Hop Scene Graph Reasoning for Visual Question Answering","created":"2021-07-13","cited_by_count":13,"area":null},{"id":"2111.09276","title":"Induce, Edit, Retrieve: Language Grounded Multimodal Schema for Instructional Video Retrieval","created":"2021-11-17","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},{"id":"2207.06403","title":"3D Concept Grounding on Neural Fields","created":"2022-07-13","cited_by_count":13,"area":null},{"id":"2211.03779","title":"CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering","created":"2022-11-07","cited_by_count":13,"area":null},{"id":"2103.10574","title":"Hopper: Multi-hop Transformer for Spatiotemporal Reasoning","created":"2021-03-19","cited_by_count":12,"area":null},{"id":"2109.01934","title":"Weakly Supervised Relative Spatial Reasoning for Visual Question Answering","created":"2021-09-04","cited_by_count":12,"area":null},{"id":"2110.09419","title":"Compositional Attention: Disentangling Search and Retrieval","created":"2021-10-18","cited_by_count":12,"area":null},{"id":"2408.02687","title":"Compositional Physical Reasoning of Objects and Events from Videos","created":"2024-08-02","cited_by_count":12,"area":null},{"id":"2103.15974","title":"Domain-robust VQA with diverse datasets and methods but no target labels","created":"2021-03-29","cited_by_count":11,"area":null},{"id":"2202.08806","title":"Grammar-Based Grounded Lexicon Learning","created":"2022-02-17","cited_by_count":11,"area":null},{"id":"2309.01073","title":"Spatial and Visual Perspective-Taking via View Rotation and Relation Reasoning for Embodied Reference Understanding","created":"2023-09-03","cited_by_count":11,"area":null},{"id":"2205.02671","title":"What is Right for Me is Not Yet Right for You: A Dataset for Grounding Relative Directions via Multi-Task Learning","created":"2022-05-05","cited_by_count":10,"area":null},{"id":"2305.00581","title":"Multimodal Graph Transformer for Multimodal Question Answering","created":"2023-04-30","cited_by_count":10,"area":null},{"id":"2204.13695","title":"Bilinear value networks","created":"2022-04-28","cited_by_count":9,"area":null},{"id":"2402.17032","title":"REFACTOR: Learning to Extract Theorems from Proofs","created":"2024-02-26","cited_by_count":9,"area":null},{"id":"2106.15550","title":"Unified Questioner Transformer for Descriptive Question Generation in Goal-Oriented Visual Dialogue","created":"2021-06-29","cited_by_count":8,"area":null},{"id":"2109.08460","title":"Neural Unification for Logic Reasoning over Natural Language","created":"2021-09-17","cited_by_count":8,"area":null},{"id":"2112.05909","title":"Neural Attention Models in Deep Learning: Survey and Taxonomy","created":"2021-12-11","cited_by_count":8,"area":null},{"id":"2112.09456","title":"Compositional Learning-based Planning for Vision POMDPs","created":"2021-12-17","cited_by_count":8,"area":null},{"id":"2207.02334","title":"Weakly Supervised Grounding for VQA in Vision-Language Transformers","created":"2022-07-05","cited_by_count":8,"area":null},{"id":"2303.01869","title":"Intrinsic Physical Concepts Discovery with Object-Centric Predictive Models","created":"2023-03-03","cited_by_count":8,"area":null},{"id":"2305.15015","title":"Measuring Faithful and Plausible Visual Grounding in VQA","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2309.11593","title":"Sentence Attention Blocks for Answer Grounding","created":"2023-09-20","cited_by_count":8,"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":"2312.10728","title":"Benchmarks for Physical Reasoning AI","created":"2023-12-17","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":"2104.05166","title":"Object-Centric Representation Learning for Video Question Answering","created":"2021-04-12","cited_by_count":7,"area":null},{"id":"2112.10572","title":"General Greedy De-bias Learning","created":"2021-12-20","cited_by_count":7,"area":null},{"id":"2210.08031","title":"Neural Attentive Circuits","created":"2022-10-14","cited_by_count":6,"area":null},{"id":"2210.15037","title":"Generalization Differences between End-to-End and Neuro-Symbolic Vision-Language Reasoning Systems","created":"2022-10-26","cited_by_count":6,"area":null},{"id":"2308.08628","title":"Learning the meanings of function words from grounded language using a visual question answering model","created":"2023-08-16","cited_by_count":6,"area":null},{"id":"2103.00519","title":"KANDINSKYPatterns -- An experimental exploration environment for Pattern Analysis and Machine Intelligence","created":"2021-02-28","cited_by_count":5,"area":null},{"id":"2401.06400","title":"Generalizing Visual Question Answering from Synthetic to Human-Written Questions via a Chain of QA with a Large Language Model","created":"2024-01-12","cited_by_count":5,"area":null},{"id":"2406.18253","title":"On the Role of Visual Grounding in VQA","created":"2024-06-26","cited_by_count":5,"area":null},{"id":"2506.08227","title":"A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks","created":"2025-06-09","cited_by_count":5,"area":null},{"id":"2508.01984","title":"IMoRe: Implicit Program-Guided Reasoning for Human Motion Q&A","created":"2025-08-04","cited_by_count":5,"area":null},{"id":"2601.02783","title":"EarthVL: A Progressive Earth Vision-Language Understanding and Generation Framework","created":"2026-01-06","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":"2208.08104","title":"Understanding Attention for Vision-and-Language Tasks","created":"2022-08-17","cited_by_count":4,"area":null},{"id":"2302.01241","title":"Diagrammatization and Abduction to Improve AI Interpretability With Domain-Aligned Explanations for Medical Diagnosis","created":"2023-02-02","cited_by_count":4,"area":null},{"id":"2303.10482","title":"Divide and Conquer: Answering Questions with Object Factorization and Compositional Reasoning","created":"2023-03-18","cited_by_count":4,"area":null},{"id":"2305.05921","title":"Decker: Double Check with Heterogeneous Knowledge for Commonsense Fact Verification","created":"2023-05-10","cited_by_count":4,"area":null},{"id":"2103.00816","title":"Contrastive Separative Coding for Self-supervised Representation Learning","created":"2021-03-01","cited_by_count":3,"area":null},{"id":"2106.01904","title":"Representing Syntax and Composition with Geometric Transformations","created":"2021-06-03","cited_by_count":3,"area":null},{"id":"2106.06147","title":"NAAQA: A Neural Architecture for Acoustic Question Answering","created":"2021-06-11","cited_by_count":3,"area":null},{"id":"2112.05419","title":"Predicting Physical World Destinations for Commands Given to Self-Driving Cars","created":"2021-12-10","cited_by_count":3,"area":null},{"id":"2205.05943","title":"Exploiting Inductive Bias in Transformers for Unsupervised Disentanglement of Syntax and Semantics with VAEs","created":"2022-05-12","cited_by_count":3,"area":null},{"id":"2208.03030","title":"ChiQA: A Large Scale Image-based Real-World Question Answering Dataset for Multi-Modal Understanding","created":"2022-08-05","cited_by_count":3,"area":null},{"id":"2208.10353","title":"Neuro-Symbolic Visual Dialog","created":"2022-08-22","cited_by_count":3,"area":null},{"id":"2211.08086","title":"Visually Grounded VQA by Lattice-based Retrieval","created":"2022-11-15","cited_by_count":3,"area":null},{"id":"2311.08695","title":"Attribute Diversity Determines the Systematicity Gap in VQA","created":"2023-11-15","cited_by_count":3,"area":null},{"id":"2312.13219","title":"Interactive Visual Task Learning for Robots","created":"2023-12-20","cited_by_count":3,"area":null},{"id":"2411.15702","title":"Editable-DeepSC: Reliable Cross-Modal Semantic Communications for Facial Editing","created":"2024-11-24","cited_by_count":3,"area":null}],"next_cursor":"100"}