{"total":89,"rows":[{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556,"area":null},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897,"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":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320,"area":null},{"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":"2110.08568","title":"ASFormer: Transformer for Action Segmentation","created":"2021-10-16","cited_by_count":168,"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":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146,"area":null},{"id":"2106.11297","title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","created":"2021-06-21","cited_by_count":127,"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":"2201.10990","title":"Learning To Recognize Procedural Activities with Distant Supervision","created":"2022-01-26","cited_by_count":85,"area":null},{"id":"2210.10352","title":"Temporal Action Segmentation: An Analysis of Modern Techniques","created":"2022-10-19","cited_by_count":85,"area":null},{"id":"2307.16368","title":"AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?","created":"2023-07-31","cited_by_count":81,"area":null},{"id":"2308.06947","title":"Knowing Where to Focus: Event-aware Transformer for Video Grounding","created":"2023-08-14","cited_by_count":79,"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":"2203.14104","title":"Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos","created":"2022-03-26","cited_by_count":50,"area":null},{"id":"2104.11452","title":"SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos","created":"2021-04-23","cited_by_count":40,"area":null},{"id":"2209.08691","title":"MECCANO: A Multimodal Egocentric Dataset for Humans Behavior Understanding in the Industrial-like Domain","created":"2022-09-19","cited_by_count":36,"area":null},{"id":"2105.02668","title":"VideoLT: Large-scale Long-tailed Video Recognition","created":"2021-05-06","cited_by_count":35,"area":null},{"id":"2105.08141","title":"VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living","created":"2021-05-17","cited_by_count":35,"area":null},{"id":"2103.10211","title":"Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning","created":"2021-03-18","cited_by_count":31,"area":null},{"id":"2210.11566","title":"Rethinking Learning Approaches for Long-Term Action Anticipation","created":"2022-10-20","cited_by_count":29,"area":null},{"id":"2311.17944","title":"PALM: Predicting Actions through Language Models","created":"2023-11-29","cited_by_count":29,"area":null},{"id":"2105.10859","title":"Coarse to Fine Multi-Resolution Temporal Convolutional Network","created":"2021-05-23","cited_by_count":28,"area":null},{"id":"2203.12856","title":"Beyond Fixation: Dynamic Window Visual Transformer","created":"2022-03-24","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":"2211.12883","title":"Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground","created":"2022-11-23","cited_by_count":27,"area":null},{"id":"2105.00067","title":"Unsupervised Discriminative Embedding for Sub-Action Learning in Complex Activities","created":"2021-04-30","cited_by_count":26,"area":null},{"id":"2103.15395","title":"No frame left behind: Full Video Action Recognition","created":"2021-03-29","cited_by_count":24,"area":null},{"id":"2212.11078","title":"C2F-TCN: A Framework for Semi and Fully Supervised Temporal Action Segmentation","created":"2022-12-20","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":"2309.16669","title":"Training a Large Video Model on a Single Machine in a Day","created":"2023-09-28","cited_by_count":20,"area":null},{"id":"2310.17942","title":"Diversifying Spatial-Temporal Perception for Video Domain Generalization","created":"2023-10-27","cited_by_count":19,"area":null},{"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":"2503.20781","title":"BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimation","created":"2025-03-26","cited_by_count":17,"area":null},{"id":"2108.06706","title":"Temporal Action Segmentation with High-level Complex Activity Labels","created":"2021-08-15","cited_by_count":16,"area":null},{"id":"2110.00529","title":"Unsupervised Motion Representation Learning with Capsule Autoencoders","created":"2021-10-01","cited_by_count":16,"area":null},{"id":"2208.00934","title":"Video Question Answering with Iterative Video-Text Co-Tokenization","created":"2022-08-01","cited_by_count":16,"area":null},{"id":"2203.08897","title":"Gate-Shift-Fuse for Video Action Recognition","created":"2022-03-16","cited_by_count":15,"area":null},{"id":"2101.06636","title":"Coarse Temporal Attention Network (CTA-Net) for Driver's Activity Recognition","created":"2021-01-17","cited_by_count":14,"area":null},{"id":"2210.04889","title":"Turbo Training with Token Dropout","created":"2022-10-10","cited_by_count":14,"area":null},{"id":"2409.06299","title":"Enhancing Long Video Understanding via Hierarchical Event-Based Memory","created":"2024-09-10","cited_by_count":14,"area":null},{"id":"2204.13340","title":"The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction","created":"2022-04-28","cited_by_count":13,"area":null},{"id":"2411.11409","title":"IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos","created":"2024-11-18","cited_by_count":12,"area":null},{"id":"2104.01198","title":"Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memories","created":"2021-04-02","cited_by_count":11,"area":null},{"id":"2110.05697","title":"Hierarchical Modeling for Task Recognition and Action Segmentation in Weakly-Labeled Instructional Videos","created":"2021-10-12","cited_by_count":11,"area":null},{"id":"2110.14381","title":"Temporal-attentive Covariance Pooling Networks for Video Recognition","created":"2021-10-27","cited_by_count":11,"area":null},{"id":"2104.00646","title":"Motion Guided Attention Fusion to Recognize Interactions from Videos","created":"2021-04-01","cited_by_count":10,"area":null},{"id":"2202.13096","title":"Continuous Human Action Recognition for Human-Machine Interaction: A Review","created":"2022-02-26","cited_by_count":10,"area":null},{"id":"2203.10694","title":"FAR: Fourier Aerial Video Recognition","created":"2022-03-21","cited_by_count":10,"area":null},{"id":"2508.01742","title":"Intention-Guided Cognitive Reasoning for Egocentric Long-Term Action Anticipation","created":"2025-08-03","cited_by_count":10,"area":null},{"id":"2311.15991","title":"DiffAnt: Diffusion Models for Action Anticipation","created":"2023-11-27","cited_by_count":9,"area":"diffusion"},{"id":"2106.03152","title":"Technical Report: Temporal Aggregate Representations","created":"2021-06-06","cited_by_count":8,"area":null},{"id":"2404.01591","title":"Language Model Guided Interpretable Video Action Reasoning","created":"2024-04-02","cited_by_count":8,"area":"lr"},{"id":"2407.10860","title":"Human-Centric Transformer for Domain Adaptive Action Recognition","created":"2024-07-15","cited_by_count":8,"area":null},{"id":"2103.11313","title":"PGT: A Progressive Method for Training Models on Long Videos","created":"2021-03-21","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":"2410.07912","title":"Understanding Spatio-Temporal Relations in Human-Object Interaction using Pyramid Graph Convolutional Network","created":"2024-10-10","cited_by_count":7,"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":"2407.06162","title":"RNNs, CNNs and Transformers in Human Action Recognition: A Survey and a Hybrid Model","created":"2024-06-02","cited_by_count":5,"area":null},{"id":"2408.17422","title":"Open-Vocabulary Action Localization with Iterative Visual Prompting","created":"2024-08-30","cited_by_count":5,"area":null},{"id":"2505.01713","title":"Vision and Intention Boost Large Language Model in Long-Term Action Anticipation","created":"2025-05-03","cited_by_count":5,"area":null},{"id":"2405.06574","title":"Deep video representation learning: a survey","created":"2024-05-10","cited_by_count":4,"area":null},{"id":"2410.21275","title":"Enhancing Action Recognition by Leveraging the Hierarchical Structure of Actions and Textual Context","created":"2024-10-28","cited_by_count":4,"area":null},{"id":"2410.22829","title":"Situational Scene Graph for Structured Human-centric Situation Understanding","created":"2024-10-30","cited_by_count":4,"area":null},{"id":"2506.23283","title":"MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition","created":"2025-06-29","cited_by_count":4,"area":"ssm"},{"id":"2503.12332","title":"VideoMAP: Toward Scalable Mamba-based Video Autoregressive Pretraining","created":"2025-03-16","cited_by_count":3,"area":"ssm"},{"id":"2504.03501","title":"LV-MAE: Learning Long Video Representations through Masked-Embedding Autoencoders","created":"2025-04-04","cited_by_count":3,"area":null},{"id":"2207.08001","title":"SVGraph: Learning Semantic Graphs from Instructional Videos","created":"2022-07-16","cited_by_count":2,"area":null},{"id":"2308.11249","title":"Video BagNet: short temporal receptive fields increase robustness in long-term action recognition","created":"2023-08-22","cited_by_count":2,"area":null},{"id":"2309.09534","title":"Selective Volume Mixup for Video Action Recognition","created":"2023-09-18","cited_by_count":2,"area":null},{"id":"2311.17118","title":"Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition","created":"2023-11-28","cited_by_count":2,"area":null},{"id":"2504.05491","title":"REEF: Relevance-Aware and Efficient LLM Adapter for Video Understanding","created":"2025-04-07","cited_by_count":2,"area":"mllm"},{"id":"2602.23294","title":"Towards Long-Form Spatio-Temporal Video Grounding","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2104.01110","title":"NAS-TC: Neural Architecture Search on Temporal Convolutions for Complex Action Recognition","created":"2021-03-17","cited_by_count":1,"area":null},{"id":"2109.02137","title":"Efficient Action Recognition Using Confidence Distillation","created":"2021-09-05","cited_by_count":1,"area":null},{"id":"2204.11929","title":"Temporal Relevance Analysis for Video Action Models","created":"2022-04-25","cited_by_count":1,"area":null},{"id":"2402.13955","title":"BEE-NET: A deep neural network to identify in-the-wild Bodily Expression of Emotions","created":"2024-02-21","cited_by_count":1,"area":null},{"id":"2510.11417","title":"Robust Ego-Exo Correspondence with Long-Term Memory","created":"2025-10-13","cited_by_count":1,"area":"moe"},{"id":"2606.14778","title":"FactCheck: Feasibility-aware Long-term Action Anticipation with Multi-agent Collaboration","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2301.11880","title":"Optical Flow Estimation in 360$^\\circ$ Videos: Dataset, Model and Application","created":"2023-01-27","cited_by_count":0,"area":null},{"id":"2407.14658","title":"A New Lightweight Hybrid Graph Convolutional Neural Network -- CNN Scheme for Scene Classification using Object Detection Inference","created":"2024-07-19","cited_by_count":0,"area":null},{"id":"2503.14524","title":"Salient Temporal Encoding for Dynamic Scene Graph Generation","created":"2025-03-15","cited_by_count":0,"area":null},{"id":"2506.16701","title":"Language-driven Description Generation and Common Sense Reasoning for Video Action Recognition","created":"2025-06-20","cited_by_count":0,"area":"lr"},{"id":"2509.09151","title":"Video Understanding by Design: How Datasets Shape Video Models","created":"2025-09-11","cited_by_count":0,"area":null}],"next_cursor":null}