{"total":82,"rows":[{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321,"area":null},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2302.03024","title":"AIM: Adapting Image Models for Efficient Video Action Recognition","created":"2023-02-06","cited_by_count":148,"area":null},{"id":"2209.07526","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","created":"2022-09-15","cited_by_count":143,"area":null},{"id":"2209.15179","title":"Physical Adversarial Attack meets Computer Vision: A Decade Survey","created":"2022-09-30","cited_by_count":67,"area":null},{"id":"2112.01514","title":"Self-supervised Video Transformer","created":"2021-12-02","cited_by_count":64,"area":null},{"id":"2108.02722","title":"Video Contrastive Learning with Global Context","created":"2021-08-05","cited_by_count":41,"area":null},{"id":"2404.16038","title":"A Survey on Generative AI and LLM for Video Generation, Understanding, and Streaming","created":"2024-01-30","cited_by_count":37,"area":null},{"id":"2110.05877","title":"OpenHands: Making Sign Language Recognition Accessible with Pose-based Pretrained Models across Languages","created":"2021-10-12","cited_by_count":31,"area":null},{"id":"2206.01038","title":"A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications","created":"2022-06-02","cited_by_count":28,"area":null},{"id":"2109.09920","title":"Survey: Transformer based Video-Language Pre-training","created":"2021-09-21","cited_by_count":27,"area":null},{"id":"2206.02846","title":"A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information","created":"2022-06-06","cited_by_count":26,"area":null},{"id":"2301.00896","title":"Efficient Robustness Assessment via Adversarial Spatial-Temporal Focus on Videos","created":"2023-01-03","cited_by_count":20,"area":null},{"id":"2407.01264","title":"SignCLIP: Connecting Text and Sign Language by Contrastive Learning","created":"2024-07-01","cited_by_count":20,"area":null},{"id":"2212.06301","title":"Egocentric Video Task Translation","created":"2022-12-13","cited_by_count":19,"area":null},{"id":"2304.01110","title":"AutoLabel: CLIP-based framework for Open-set Video Domain Adaptation","created":"2023-04-03","cited_by_count":18,"area":null},{"id":"2110.07692","title":"Shaping embodied agent behavior with activity-context priors from egocentric video","created":"2021-10-14","cited_by_count":17,"area":null},{"id":"2207.06261","title":"Is Appearance Free Action Recognition Possible?","created":"2022-07-13","cited_by_count":16,"area":null},{"id":"2308.09139","title":"The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation","created":"2023-08-17","cited_by_count":16,"area":null},{"id":"2503.14378","title":"Impossible Videos","created":"2025-03-18","cited_by_count":16,"area":null},{"id":"2108.02110","title":"Recursive Fusion and Deformable Spatiotemporal Attention for Video Compression Artifact Reduction","created":"2021-08-04","cited_by_count":14,"area":null},{"id":"2410.13790","title":"MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotations","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2105.08647","title":"IntFormer: Predicting pedestrian intention with the aid of the Transformer architecture","created":"2021-05-18","cited_by_count":13,"area":null},{"id":"2208.04897","title":"Sports Video Analysis on Large-Scale Data","created":"2022-08-09","cited_by_count":13,"area":null},{"id":"2306.07703","title":"E2E-LOAD: End-to-End Long-form Online Action Detection","created":"2023-06-13","cited_by_count":8,"area":null},{"id":"2206.01009","title":"Unified Recurrence Modeling for Video Action Anticipation","created":"2022-06-02","cited_by_count":7,"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":"2211.01783","title":"Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks","created":"2022-11-03","cited_by_count":7,"area":null},{"id":"2501.12681","title":"Can masking background and object reduce static bias for zero-shot action recognition?","created":"2025-01-22","cited_by_count":6,"area":null},{"id":"2110.08814","title":"TEAM-Net: Multi-modal Learning for Video Action Recognition with Partial Decoding","created":"2021-10-17","cited_by_count":5,"area":null},{"id":"2203.02489","title":"Pedestrian Stop and Go Forecasting with Hybrid Feature Fusion","created":"2022-03-04","cited_by_count":5,"area":null},{"id":"2207.12730","title":"P2ANet: A Dataset and Benchmark for Dense Action Detection from Table Tennis Match Broadcasting Videos","created":"2022-07-26","cited_by_count":5,"area":null},{"id":"2304.10073","title":"Video-based Contrastive Learning on Decision Trees: from Action Recognition to Autism Diagnosis","created":"2023-04-20","cited_by_count":5,"area":null},{"id":"2305.07825","title":"Student Classroom Behavior Detection based on YOLOv7-BRA and Multi-Model Fusion","created":"2023-05-13","cited_by_count":5,"area":null},{"id":"2310.02522","title":"SCB-Dataset3: A Benchmark for Detecting Student Classroom Behavior","created":"2023-10-04","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":"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":"2106.08323","title":"VidHarm: A Clip Based Dataset for Harmful Content Detection","created":"2021-06-15","cited_by_count":4,"area":null},{"id":"2111.09641","title":"Evaluating Transformers for Lightweight Action Recognition","created":"2021-11-18","cited_by_count":4,"area":null},{"id":"2207.09927","title":"ViGAT: Bottom-up event recognition and explanation in video using factorized graph attention network","created":"2022-07-20","cited_by_count":4,"area":null},{"id":"2301.06187","title":"CNN-Based Action Recognition and Pose Estimation for Classifying Animal Behavior from Videos: A Survey","created":"2023-01-15","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":"2403.06978","title":"Attention Prompt Tuning: Parameter-efficient Adaptation of Pre-trained Models for Spatiotemporal Modeling","created":"2024-03-11","cited_by_count":4,"area":null},{"id":"2204.09166","title":"Performance Evaluation of Action Recognition Models on Low Quality Videos","created":"2022-04-19","cited_by_count":3,"area":null},{"id":"2210.07983","title":"Improving Transfer Learning with a Dual Image and Video Transformer for Multi-label Movie Trailer Genre Classification","created":"2022-10-14","cited_by_count":3,"area":null},{"id":"2302.01921","title":"Transformers in Action Recognition: A Review on Temporal Modeling","created":"2022-12-29","cited_by_count":3,"area":null},{"id":"2304.14104","title":"Learning Human-Human Interactions in Images from Weak Textual Supervision","created":"2023-04-27","cited_by_count":3,"area":null},{"id":"2306.03318","title":"Student Classroom Behavior Detection based on Improved YOLOv7","created":"2023-06-06","cited_by_count":3,"area":null},{"id":"2401.02052","title":"Encoder-Decoder Based Long Short-Term Memory (LSTM) Model for Video Captioning","created":"2023-10-02","cited_by_count":3,"area":null},{"id":"2404.06243","title":"ActNetFormer: Transformer-ResNet Hybrid Method for Semi-Supervised Action Recognition in Videos","created":"2024-04-09","cited_by_count":3,"area":null},{"id":"2103.05101","title":"Video Action Recognition Using spatio-temporal optical flow video frames","created":"2021-02-05","cited_by_count":2,"area":null},{"id":"2206.11459","title":"Explore Spatio-temporal Aggregation for Insubstantial Object Detection: Benchmark Dataset and Baseline","created":"2022-06-23","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":"2408.05421","title":"EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action Recognition","created":"2024-08-10","cited_by_count":2,"area":null},{"id":"2409.09678","title":"A Comprehensive Methodological Survey of Human Activity Recognition Across Divers Data Modalities","created":"2024-09-15","cited_by_count":2,"area":null},{"id":"2411.00630","title":"STAA: Spatio-Temporal Attention Attribution for Real-Time Interpreting Transformer-based Video Models","created":"2024-11-01","cited_by_count":2,"area":null},{"id":"2204.10160","title":"A Multi-Person Video Dataset Annotation Method of Spatio-Temporally Actions","created":"2022-04-21","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":"2206.08632","title":"Learning Using Privileged Information for Zero-Shot Action Recognition","created":"2022-06-17","cited_by_count":1,"area":null},{"id":"2212.11030","title":"Deep set conditioned latent representations for action recognition","created":"2022-12-21","cited_by_count":1,"area":null},{"id":"2301.07565","title":"Gated-ViGAT: Efficient Bottom-Up Event Recognition and Explanation Using a New Frame Selection Policy and Gating Mechanism","created":"2023-01-18","cited_by_count":1,"area":null},{"id":"2302.02755","title":"Fine-Grained Action Detection with RGB and Pose Information using Two Stream Convolutional Networks","created":"2023-02-06","cited_by_count":1,"area":null},{"id":"2309.06951","title":"TransNet: A Transfer Learning-Based Network for Human Action Recognition","created":"2023-09-13","cited_by_count":1,"area":null},{"id":"2406.01894","title":"SVASTIN: Sparse Video Adversarial Attack via Spatio-Temporal Invertible Neural Networks","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2411.16973","title":"SEMU-Net: A Segmentation-based Corrector for Fabrication Process Variations of Nanophotonics with Microscopic Images","created":"2024-11-25","cited_by_count":1,"area":null},{"id":"2501.11653","title":"Dynamic Scene Understanding from Vision-Language Representations","created":"2025-01-20","cited_by_count":1,"area":null},{"id":"2511.02473","title":"MVAFormer: RGB-based Multi-View Spatio-Temporal Action Recognition with Transformer","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2608.03269","title":"Efficient Video Dataset Distillation via Cluster-Guided Prototype Blending","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2203.12344","title":"How Do You Do It? Fine-Grained Action Understanding with Pseudo-Adverbs","created":"2022-03-23","cited_by_count":0,"area":null},{"id":"2207.13306","title":"Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition","created":"2022-07-27","cited_by_count":0,"area":null},{"id":"2208.14856","title":"Active Learning with Effective Scoring Functions for Semi-Supervised Temporal Action Localization","created":"2022-08-31","cited_by_count":0,"area":null},{"id":"2303.07317","title":"Nearest-Neighbor Inter-Intra Contrastive Learning from Unlabeled Videos","created":"2023-03-13","cited_by_count":0,"area":null},{"id":"2308.10533","title":"Joint learning of images and videos with a single Vision Transformer","created":"2023-08-21","cited_by_count":0,"area":null},{"id":"2310.06339","title":"Automatic nodule identification and differentiation in ultrasound videos to facilitate per-nodule examination","created":"2023-10-10","cited_by_count":0,"area":null},{"id":"2310.08451","title":"Proving the Potential of Skeleton Based Action Recognition to Automate the Analysis of Manual Processes","created":"2023-10-12","cited_by_count":0,"area":null},{"id":"2310.16267","title":"Student Classroom Behavior Detection based on Spatio-Temporal Network and Multi-Model Fusion","created":"2023-10-25","cited_by_count":0,"area":null},{"id":"2401.14675","title":"Multi-model learning by sequential reading of untrimmed videos for action recognition","created":"2024-01-26","cited_by_count":0,"area":null},{"id":"2410.18717","title":"Low-Latency Video Anonymization for Crowd Anomaly Detection: Privacy Versus Performance","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2507.02997","title":"What to Do Next? Memorizing skills from Egocentric Instructional Video","created":"2025-07-01","cited_by_count":0,"area":null},{"id":"2509.05695","title":"Leveraging Vision-Language Large Models for Interpretable Video Action Recognition with Semantic Tokenization","created":"2025-09-06","cited_by_count":0,"area":null},{"id":"2601.14086","title":"Two-Stream temporal transformer for video action classification","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2606.27777","title":"TRUST: Efficient Abdominal Trauma Recognition via Image-to-Ultrasound-Video Transfer Learning","created":"2026-06-26","cited_by_count":0,"area":null}],"next_cursor":null}