{"total":146,"rows":[{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680,"area":null},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576,"area":null},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542,"area":null},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519,"area":null},{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328,"area":"ssm"},{"id":"2403.11481","title":"VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding","created":"2024-03-18","cited_by_count":229,"area":"mllm"},{"id":"2404.05726","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","created":"2024-04-08","cited_by_count":229,"area":"mllm"},{"id":"2201.08383","title":"MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition","created":"2022-01-20","cited_by_count":189,"area":null},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178,"area":null},{"id":"2404.03384","title":"LongVLM: Efficient Long Video Understanding via Large Language Models","created":"2024-04-04","cited_by_count":147,"area":null},{"id":"2208.02797","title":"Vision-Centric BEV Perception: A Survey","created":"2022-08-04","cited_by_count":126,"area":null},{"id":"2405.08813","title":"CinePile: A Long Video Question Answering Dataset and Benchmark","created":"2024-05-14","cited_by_count":114,"area":null},{"id":"2204.01696","title":"Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos","created":"2022-04-04","cited_by_count":111,"area":null},{"id":"2204.01692","title":"Long Movie Clip Classification with State-Space Video Models","created":"2022-04-04","cited_by_count":106,"area":null},{"id":"2303.14526","title":"Selective Structured State-Spaces for Long-Form Video Understanding","created":"2023-03-25","cited_by_count":105,"area":"ssm"},{"id":"2508.04416","title":"Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning","created":"2025-08-06","cited_by_count":91,"area":"lr"},{"id":"2107.03377","title":"Long Short-Term Transformer for Online Action Detection","created":"2021-07-07","cited_by_count":88,"area":null},{"id":"2310.19773","title":"MM-VID: Advancing Video Understanding with GPT-4V(ision)","created":"2023-10-30","cited_by_count":83,"area":null},{"id":"2404.01297","title":"Streaming Dense Video Captioning","created":"2024-04-01","cited_by_count":82,"area":null},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73,"area":null},{"id":"2404.17176","title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","created":"2024-04-26","cited_by_count":73,"area":null},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66,"area":null},{"id":"2404.16112","title":"Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challenges","created":"2024-04-24","cited_by_count":64,"area":"ssm"},{"id":"2504.15271","title":"Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models","created":"2025-04-21","cited_by_count":64,"area":"mllm"},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2210.06031","title":"Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning","created":"2022-10-12","cited_by_count":59,"area":null},{"id":"2205.08508","title":"A CLIP-Hitchhiker's Guide to Long Video Retrieval","created":"2022-05-17","cited_by_count":57,"area":null},{"id":"2404.04346","title":"Koala: Key frame-conditioned long video-LLM","created":"2024-04-05","cited_by_count":57,"area":null},{"id":"2412.10471","title":"VCA: Video Curious Agent for Long Video Understanding","created":"2024-12-12","cited_by_count":56,"area":"agents"},{"id":"2212.09522","title":"MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering","created":"2022-12-19","cited_by_count":55,"area":null},{"id":"2212.14427","title":"Efficient Movie Scene Detection using State-Space Transformers","created":"2022-12-29","cited_by_count":51,"area":null},{"id":"2312.03391","title":"Action Scene Graphs for Long-Form Understanding of Egocentric Videos","created":"2023-12-06","cited_by_count":51,"area":null},{"id":"2310.19060","title":"TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding","created":"2023-10-29","cited_by_count":49,"area":null},{"id":"2210.06583","title":"S4ND: Modeling Images and Videos as Multidimensional Signals Using State Spaces","created":"2022-10-12","cited_by_count":41,"area":null},{"id":"2406.08659","title":"Vivid-ZOO: Multi-View Video Generation with Diffusion Model","created":"2024-06-12","cited_by_count":40,"area":"diffusion"},{"id":"2305.06343","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","created":"2023-05-10","cited_by_count":39,"area":null},{"id":"2312.07395","title":"A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames","created":"2023-12-12","cited_by_count":34,"area":null},{"id":"2304.01199","title":"On the Benefits of 3D Pose and Tracking for Human Action Recognition","created":"2023-04-03","cited_by_count":32,"area":null},{"id":"2210.12686","title":"Holistic Interaction Transformer Network for Action Detection","created":"2022-10-23","cited_by_count":28,"area":null},{"id":"2502.06020","title":"Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding","created":"2025-02-09","cited_by_count":28,"area":null},{"id":"2209.10918","title":"CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding","created":"2022-09-22","cited_by_count":27,"area":null},{"id":"2207.09812","title":"The Anatomy of Video Editing: A Dataset and Benchmark Suite for AI-Assisted Video Editing","created":"2022-07-20","cited_by_count":25,"area":null},{"id":"2312.04817","title":"LvBench: A Benchmark for Long-form Video Understanding with Versatile Multi-modal Question Answering","created":"2023-12-08","cited_by_count":25,"area":null},{"id":"2407.08476","title":"VideoMamba: Spatio-Temporal Selective State Space Model","created":"2024-07-11","cited_by_count":25,"area":"ssm"},{"id":"2412.09582","title":"Neptune: The Long Orbit to Benchmarking Long Video Understanding","created":"2024-12-12","cited_by_count":25,"area":null},{"id":"2311.00180","title":"Object-centric Video Representation for Long-term Action Anticipation","created":"2023-10-31","cited_by_count":24,"area":null},{"id":"2501.00358","title":"Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding","created":"2024-12-31","cited_by_count":24,"area":null},{"id":"2111.11044","title":"Exploring Segment-level Semantics for Online Phase Recognition from Surgical Videos","created":"2021-11-22","cited_by_count":23,"area":null},{"id":"2410.23782","title":"Video Token Merging for Long-form Video Understanding","created":"2024-10-31","cited_by_count":23,"area":"inference"},{"id":"2207.11365","title":"EgoEnv: Human-centric environment representations from egocentric video","created":"2022-07-22","cited_by_count":22,"area":null},{"id":"2306.11726","title":"How can objects help action recognition?","created":"2023-06-20","cited_by_count":21,"area":null},{"id":"2204.03101","title":"Hierarchical Self-supervised Representation Learning for Movie Understanding","created":"2022-04-06","cited_by_count":19,"area":null},{"id":"2206.07148","title":"It's Time for Artistic Correspondence in Music and Video","created":"2022-06-14","cited_by_count":18,"area":null},{"id":"2507.09876","title":"ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language Models","created":"2025-07-14","cited_by_count":18,"area":"lr"},{"id":"2503.08585","title":"HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding","created":"2025-03-11","cited_by_count":17,"area":"mllm"},{"id":"2208.00934","title":"Video Question Answering with Iterative Video-Text Co-Tokenization","created":"2022-08-01","cited_by_count":16,"area":null},{"id":"2210.11065","title":"MovieCLIP: Visual Scene Recognition in Movies","created":"2022-10-20","cited_by_count":16,"area":null},{"id":"2403.11021","title":"Towards Neuro-Symbolic Video Understanding","created":"2024-03-16","cited_by_count":16,"area":null},{"id":"2407.21757","title":"Learning Video Context as Interleaved Multimodal Sequences","created":"2024-07-31","cited_by_count":16,"area":null},{"id":"2204.02509","title":"Depth-Guided Sparse Structure-from-Motion for Movies and TV Shows","created":"2022-04-05","cited_by_count":15,"area":null},{"id":"2311.05698","title":"Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities","created":"2023-11-09","cited_by_count":15,"area":null},{"id":"2212.04821","title":"PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Data","created":"2022-12-08","cited_by_count":14,"area":null},{"id":"2503.16032","title":"Agentic Keyframe Search for Video Question Answering","created":"2025-03-20","cited_by_count":13,"area":"agents"},{"id":"2406.10221","title":"Long Story Short: Story-level Video Understanding from 20K Short Films","created":"2024-06-14","cited_by_count":12,"area":"mllm"},{"id":"2411.00489","title":"Human-inspired Perspectives: A Survey on AI Long-term Memory","created":"2024-11-01","cited_by_count":12,"area":null},{"id":"2503.19851","title":"Towards Online Multi-Modal Social Interaction Understanding","created":"2025-03-25","cited_by_count":12,"area":null},{"id":"2202.10650","title":"Movies2Scenes: Using Movie Metadata to Learn Scene Representation","created":"2022-02-22","cited_by_count":11,"area":null},{"id":"2305.09758","title":"A Video Is Worth 4096 Tokens: Verbalize Videos To Understand Them In Zero Shot","created":"2023-05-16","cited_by_count":11,"area":null},{"id":"2408.17443","title":"HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics","created":"2024-08-30","cited_by_count":11,"area":null},{"id":"2309.10171","title":"Specification-Driven Video Search via Foundation Models and Formal Verification","created":"2023-09-18","cited_by_count":10,"area":null},{"id":"2406.19006","title":"Snakes and Ladders: Two Steps Up for VideoMamba","created":"2024-06-27","cited_by_count":10,"area":"ssm"},{"id":"2502.20361","title":"OpenTAD: A Unified Framework and Comprehensive Study of Temporal Action Detection","created":"2025-02-27","cited_by_count":10,"area":null},{"id":"2508.09486","title":"Video-EM: Event-Centric Episodic Memory for Long-Form Video Understanding","created":"2025-08-13","cited_by_count":10,"area":null},{"id":"2308.07213","title":"Human-centered NLP Fact-checking: Co-Designing with Fact-checkers using Matchmaking for AI","created":"2023-08-14","cited_by_count":9,"area":null},{"id":"2309.00359","title":"Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior","created":"2023-09-01","cited_by_count":9,"area":null},{"id":"2203.05711","title":"Synopses of Movie Narratives: a Video-Language Dataset for Story Understanding","created":"2022-03-11","cited_by_count":8,"area":null},{"id":"2405.19723","title":"Encoding and Controlling Global Semantics for Long-form Video Question Answering","created":"2024-05-30","cited_by_count":8,"area":null},{"id":"2506.06518","title":"A Systematic Review of Poisoning Attacks Against Large Language Models","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2210.13827","title":"End-to-end Transformer for Compressed Video Quality Enhancement","created":"2022-10-25","cited_by_count":7,"area":null},{"id":"2211.02178","title":"Zero-shot Video Moment Retrieval With Off-the-Shelf Models","created":"2022-11-03","cited_by_count":7,"area":null},{"id":"2308.09775","title":"Long-range Multimodal Pretraining for Movie Understanding","created":"2023-08-18","cited_by_count":7,"area":null},{"id":"2309.11569","title":"Revisiting Kernel Temporal Segmentation as an Adaptive Tokenizer for Long-form Video Understanding","created":"2023-09-20","cited_by_count":7,"area":null},{"id":"2311.01444","title":"LabelFormer: Object Trajectory Refinement for Offboard Perception from LiDAR Point Clouds","created":"2023-11-02","cited_by_count":7,"area":null},{"id":"2411.12593","title":"AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction","created":"2024-11-19","cited_by_count":7,"area":null},{"id":"2304.05634","title":"How you feelin'? Learning Emotions and Mental States in Movie Scenes","created":"2023-04-12","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":"2503.04058","title":"EVE: Towards End-to-End Video Subtitle Extraction with Vision-Language Models","created":"2025-03-06","cited_by_count":6,"area":"mllm"},{"id":"2211.06023","title":"Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization Tasks","created":"2022-11-11","cited_by_count":5,"area":null},{"id":"2402.01335","title":"BehAVE: Behaviour Alignment of Video Game Encodings","created":"2024-02-02","cited_by_count":5,"area":null},{"id":"2404.00973","title":"VideoDistill: Language-aware Vision Distillation for Video Question Answering","created":"2024-04-01","cited_by_count":5,"area":null},{"id":"2410.19809","title":"ScreenWriter: Automatic Screenplay Generation and Movie Summarisation","created":"2024-10-17","cited_by_count":5,"area":null},{"id":"2503.17975","title":"Shot Sequence Ordering for Video Editing: Benchmarks, Metrics, and Cinematology-Inspired Computing Methods","created":"2025-03-23","cited_by_count":5,"area":null},{"id":"2208.01753","title":"Two-Stream Transformer Architecture for Long Video Understanding","created":"2022-08-02","cited_by_count":4,"area":null},{"id":"2309.04723","title":"Frequency-Aware Self-Supervised Long-Tailed Learning","created":"2023-09-09","cited_by_count":4,"area":null},{"id":"2309.05943","title":"Knowledge-Guided Short-Context Action Anticipation in Human-Centric Videos","created":"2023-09-12","cited_by_count":4,"area":null},{"id":"2503.13707","title":"Long-VMNet: Accelerating Long-Form Video Understanding via Fixed Memory","created":"2025-03-17","cited_by_count":4,"area":null},{"id":"2505.17536","title":"Multimodal Conversation Structure Understanding","created":"2025-05-23","cited_by_count":4,"area":"mllm"},{"id":"2512.09354","title":"Video-QTR: Query-Driven Temporal Reasoning Framework for Lightweight Video Understanding","created":"2025-12-10","cited_by_count":4,"area":"lr"},{"id":"2109.08730","title":"Unsupervised View-Invariant Human Posture Representation","created":"2021-09-17","cited_by_count":3,"area":null},{"id":"2304.05600","title":"Looking Similar, Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning","created":"2023-04-12","cited_by_count":3,"area":null}],"next_cursor":"100"}