{"total":137,"rows":[{"id":"2403.00476","title":"TempCompass: Do Video LLMs Really Understand Videos?","created":"2024-03-01","cited_by_count":363,"area":null},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314,"area":"lr"},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248,"area":"wm"},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213,"area":null},{"id":"2106.02036","title":"Anticipative Video Transformer","created":"2021-06-03","cited_by_count":200,"area":null},{"id":"2206.01720","title":"Revisiting the \"Video\" in Video-Language Understanding","created":"2022-06-03","cited_by_count":169,"area":null},{"id":"2206.07764","title":"SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos","created":"2022-06-15","cited_by_count":166,"area":null},{"id":"2205.14065","title":"Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos","created":"2022-05-27","cited_by_count":139,"area":null},{"id":"2107.03438","title":"LanguageRefer: Spatial-Language Model for 3D Visual Grounding","created":"2021-07-07","cited_by_count":89,"area":null},{"id":"2410.05643","title":"TRACE: Temporal Grounding Video LLM via Causal Event Modeling","created":"2024-10-08","cited_by_count":89,"area":null},{"id":"2112.02815","title":"Make It Move: Controllable Image-to-Video Generation with Text Descriptions","created":"2021-12-06","cited_by_count":88,"area":null},{"id":"2103.01197","title":"Coordination Among Neural Modules Through a Shared Global Workspace","created":"2021-03-01","cited_by_count":85,"area":null},{"id":"2106.03849","title":"SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition","created":"2021-06-07","cited_by_count":69,"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":"2212.05136","title":"CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection","created":"2022-12-09","cited_by_count":67,"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":"2110.10189","title":"StructFormer: Learning Spatial Structure for Language-Guided Semantic Rearrangement of Novel Objects","created":"2021-10-19","cited_by_count":59,"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":"2311.17404","title":"VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models","created":"2023-11-29","cited_by_count":55,"area":null},{"id":"2107.00848","title":"Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning","created":"2021-07-02","cited_by_count":53,"area":null},{"id":"2506.09849","title":"IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments","created":"2025-06-11","cited_by_count":52,"area":null},{"id":"2305.11173","title":"Going Denser with Open-Vocabulary Part Segmentation","created":"2023-05-18","cited_by_count":51,"area":null},{"id":"2109.03891","title":"SORNet: Spatial Object-Centric Representations for Sequential Manipulation","created":"2021-09-08","cited_by_count":48,"area":null},{"id":"2203.10159","title":"Discovering Objects that Can Move","created":"2022-03-18","cited_by_count":44,"area":null},{"id":"2503.13646","title":"Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos","created":"2025-03-17","cited_by_count":44,"area":"mllm"},{"id":"2205.07844","title":"Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motion","created":"2022-05-16","cited_by_count":42,"area":null},{"id":"2302.04752","title":"Benchmarks for Automated Commonsense Reasoning: A Survey","created":"2023-02-09","cited_by_count":40,"area":"lr"},{"id":"2103.14232","title":"ACRE: Abstract Causal REasoning Beyond Covariation","created":"2021-03-26","cited_by_count":30,"area":null},{"id":"2202.09277","title":"(2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answering","created":"2022-02-18","cited_by_count":30,"area":null},{"id":"2405.03690","title":"How Good is my Video LMM? Complex Video Reasoning and Robustness Evaluation Suite for Video-LMMs","created":"2024-05-06","cited_by_count":30,"area":"lr"},{"id":"2107.09240","title":"Generative Video Transformer: Can Objects be the Words?","created":"2021-07-20","cited_by_count":24,"area":null},{"id":"2207.10075","title":"Is an Object-Centric Video Representation Beneficial for Transfer?","created":"2022-07-20","cited_by_count":24,"area":null},{"id":"2506.21876","title":"Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation","created":"2025-06-27","cited_by_count":24,"area":"wm"},{"id":"2409.17647","title":"MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning","created":"2024-09-26","cited_by_count":23,"area":"lr"},{"id":"2412.01800","title":"PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos","created":"2024-12-02","cited_by_count":22,"area":null},{"id":"2511.16668","title":"V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation Models","created":"2025-11-20","cited_by_count":22,"area":"lr"},{"id":"2109.03351","title":"Capturing the objects of vision with neural networks","created":"2021-09-07","cited_by_count":21,"area":null},{"id":"2205.13349","title":"Learning What and Where: Disentangling Location and Identity Tracking Without Supervision","created":"2022-05-26","cited_by_count":21,"area":null},{"id":"2501.05453","title":"An Empirical Study of Autoregressive Pre-training from Videos","created":"2025-01-09","cited_by_count":21,"area":null},{"id":"2103.00336","title":"Transformers with Competitive Ensembles of Independent Mechanisms","created":"2021-02-27","cited_by_count":19,"area":null},{"id":"2204.01784","title":"Object Permanence Emerges in a Random Walk along Memory","created":"2022-04-04","cited_by_count":18,"area":null},{"id":"2406.00622","title":"Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering","created":"2024-06-02","cited_by_count":18,"area":"mllm"},{"id":"2204.10916","title":"Revealing Occlusions with 4D Neural Fields","created":"2022-04-22","cited_by_count":17,"area":null},{"id":"2303.17842","title":"Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learning","created":"2023-03-31","cited_by_count":17,"area":null},{"id":"2306.00503","title":"MEWL: Few-shot multimodal word learning with referential uncertainty","created":"2023-06-01","cited_by_count":17,"area":null},{"id":"2406.12272","title":"Slot State Space Models","created":"2024-06-18","cited_by_count":17,"area":"ssm"},{"id":"2412.17759","title":"Survey of Large Multimodal Model Datasets, Application Categories and Taxonomy","created":"2024-12-23","cited_by_count":17,"area":"mllm"},{"id":"2205.06907","title":"Multimodal Conversational AI: A Survey of Datasets and Approaches","created":"2022-05-13","cited_by_count":16,"area":null},{"id":"2204.07190","title":"Measuring Compositional Consistency for Video Question Answering","created":"2022-04-14","cited_by_count":15,"area":null},{"id":"2205.01657","title":"Cross-modal Representation Learning for Zero-shot Action Recognition","created":"2022-05-03","cited_by_count":15,"area":null},{"id":"2305.03052","title":"Tracking through Containers and Occluders in the Wild","created":"2023-05-04","cited_by_count":15,"area":null},{"id":"2309.00233","title":"Object-Centric Multiple Object Tracking","created":"2023-09-01","cited_by_count":15,"area":null},{"id":"2412.10925","title":"Video Representation Learning with Joint-Embedding Predictive Architectures","created":"2024-12-14","cited_by_count":15,"area":null},{"id":"2306.17778","title":"Look, Remember and Reason: Grounded reasoning in videos with language models","created":"2023-06-30","cited_by_count":14,"area":"lr"},{"id":"2412.13845","title":"Do Language Models Understand Time?","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2101.00151","title":"DVD: A Diagnostic Dataset for Multi-step Reasoning in Video Grounded Dialogue","created":"2021-01-01","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":"2110.06257","title":"Causal Discovery from Conditionally Stationary Time Series","created":"2021-10-12","cited_by_count":12,"area":null},{"id":"2203.05928","title":"TFCNet: Temporal Fully Connected Networks for Static Unbiased Temporal Reasoning","created":"2022-03-11","cited_by_count":12,"area":null},{"id":"2402.03019","title":"Taylor Videos for Action Recognition","created":"2024-02-05","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":"2512.14691","title":"MMGR: Multi-Modal Generative Reasoning Benchmark and Evaluation","created":"2025-12-16","cited_by_count":12,"area":"lr"},{"id":"2310.03635","title":"CLEVRER-Humans: Describing Physical and Causal Events the Human Way","created":"2023-10-05","cited_by_count":11,"area":null},{"id":"2108.13696","title":"Phy-Q as a measure for physical reasoning intelligence","created":"2021-08-31","cited_by_count":10,"area":null},{"id":"2201.10394","title":"Capturing Temporal Information in a Single Frame: Channel Sampling Strategies for Action Recognition","created":"2022-01-25","cited_by_count":10,"area":null},{"id":"2411.09105","title":"VideoCogQA: A Controllable Benchmark for Evaluating Cognitive Abilities in Video-Language Models","created":"2024-11-14","cited_by_count":10,"area":null},{"id":"2510.19788","title":"Benchmarking World-Model Learning with Environment-Level Queries","created":"2025-10-22","cited_by_count":10,"area":"wm"},{"id":"2105.14207","title":"Maintaining Common Ground in Dynamic Environments","created":"2021-05-29","cited_by_count":9,"area":null},{"id":"2108.06180","title":"SPACE: A Simulator for Physical Interactions and Causal Learning in 3D Environments","created":"2021-08-13","cited_by_count":9,"area":null},{"id":"2104.01122","title":"M3L: Language-based Video Editing via Multi-Modal Multi-Level Transformers","created":"2021-04-02","cited_by_count":8,"area":null},{"id":"2206.09203","title":"Interactive Visual Reasoning under Uncertainty","created":"2022-06-18","cited_by_count":8,"area":"lr"},{"id":"2207.13738","title":"Break and Make: Interactive Structural Understanding Using LEGO Bricks","created":"2022-07-27","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":"2305.18890","title":"Sensitivity of Slot-Based Object-Centric Models to their Number of Slots","created":"2023-05-30","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":"2605.27589","title":"What-If World: A Causal Benchmark for General World Models in Embodied Scenarios","created":"2026-05-26","cited_by_count":8,"area":"wm"},{"id":"2303.05323","title":"Controllable Video Generation by Learning the Underlying Dynamical System with Neural ODE","created":"2023-03-09","cited_by_count":7,"area":null},{"id":"2104.03424","title":"Track, Check, Repeat: An EM Approach to Unsupervised Tracking","created":"2021-04-07","cited_by_count":6,"area":null},{"id":"2206.07898","title":"Multimodal Dialogue State Tracking","created":"2022-06-16","cited_by_count":6,"area":null},{"id":"2308.11244","title":"Are current long-term video understanding datasets long-term?","created":"2023-08-22","cited_by_count":6,"area":null},{"id":"2403.09669","title":"STREAM: Spatio-TempoRal Evaluation and Analysis Metric for Video Generative Models","created":"2024-01-30","cited_by_count":6,"area":null},{"id":"2411.10371","title":"A Survey of Event Causality Identification: Taxonomy, Challenges, Assessment, and Prospects","created":"2024-11-15","cited_by_count":6,"area":null},{"id":"2308.06701","title":"Camouflaged Image Synthesis Is All You Need to Boost Camouflaged Detection","created":"2023-08-13","cited_by_count":5,"area":null},{"id":"2410.01926","title":"MARPLE: A Benchmark for Long-Horizon Inference","created":"2024-10-02","cited_by_count":5,"area":null},{"id":"2501.07227","title":"MECD+: Unlocking Event-Level Causal Graph Discovery for Video Reasoning","created":"2025-01-13","cited_by_count":5,"area":"lr"},{"id":"2502.21201","title":"The PanAf-FGBG Dataset: Understanding the Impact of Backgrounds in Wildlife Behaviour Recognition","created":"2025-02-28","cited_by_count":5,"area":null},{"id":"2102.07355","title":"Win-Fail Action Recognition","created":"2021-02-15","cited_by_count":4,"area":null},{"id":"2110.06912","title":"OPEn: An Open-ended Physics Environment for Learning Without a Task","created":"2021-10-13","cited_by_count":4,"area":null},{"id":"2207.05182","title":"Fine-grained Activities of People Worldwide","created":"2022-07-11","cited_by_count":4,"area":null},{"id":"2310.10372","title":"Learning Object Permanence from Videos via Latent Imaginations","created":"2023-10-16","cited_by_count":4,"area":null},{"id":"2504.05925","title":"SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2512.00736","title":"REM: Evaluating LLM Embodied Spatial Reasoning through Multi-Frame Trajectories","created":"2025-11-30","cited_by_count":4,"area":"lr"},{"id":"2512.14870","title":"HERBench: A Benchmark for Multi-Evidence Integration in Video Question Answering","created":"2025-12-16","cited_by_count":4,"area":null},{"id":"2206.04003","title":"Patch-based Object-centric Transformers for Efficient Video Generation","created":"2022-06-08","cited_by_count":3,"area":null},{"id":"2303.06367","title":"Probing neural representations of scene perception in a hippocampally dependent task using artificial neural networks","created":"2023-03-11","cited_by_count":3,"area":null},{"id":"2305.01928","title":"Visual Transformation Telling","created":"2023-05-03","cited_by_count":3,"area":null},{"id":"2309.06680","title":"STUPD: A Synthetic Dataset for Spatial and Temporal Relation Reasoning","created":"2023-09-13","cited_by_count":3,"area":"lr"},{"id":"2402.13146","title":"OLViT: Multi-Modal State Tracking via Attention-Based Embeddings for Video-Grounded Dialog","created":"2024-02-20","cited_by_count":3,"area":null},{"id":"2407.02218","title":"Multi-Modal Video Dialog State Tracking in the Wild","created":"2024-07-02","cited_by_count":3,"area":null}],"next_cursor":"100"}