{"total":83,"rows":[{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464,"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":"2204.03646","title":"FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment","created":"2022-04-07","cited_by_count":107,"area":null},{"id":"2107.11711","title":"Temporal-wise Attention Spiking Neural Networks for Event Streams Classification","created":"2021-07-25","cited_by_count":106,"area":null},{"id":"2209.12354","title":"InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interaction","created":"2022-09-26","cited_by_count":93,"area":null},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73,"area":null},{"id":"2104.09496","title":"Temporal Query Networks for Fine-grained Video Understanding","created":"2021-04-19","cited_by_count":68,"area":null},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66,"area":null},{"id":"2302.06646","title":"Simple Hardware-Efficient Long Convolutions for Sequence Modeling","created":"2023-02-13","cited_by_count":62,"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":"2105.05226","title":"Home Action Genome: Cooperative Compositional Action Understanding","created":"2021-05-11","cited_by_count":53,"area":null},{"id":"2104.09952","title":"MGSampler: An Explainable Sampling Strategy for Video Action Recognition","created":"2021-04-20","cited_by_count":49,"area":null},{"id":"2203.09773","title":"Local-Global Context Aware Transformer for Language-Guided Video Segmentation","created":"2022-03-18","cited_by_count":41,"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":"2103.10211","title":"Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning","created":"2021-03-18","cited_by_count":31,"area":null},{"id":"2103.01302","title":"Coarse-Fine Networks for Temporal Activity Detection in Videos","created":"2021-03-01","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":"2107.00606","title":"Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition","created":"2021-07-01","cited_by_count":24,"area":null},{"id":"2111.07774","title":"D^2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos","created":"2021-11-15","cited_by_count":20,"area":null},{"id":"2102.07624","title":"RMS-Net: Regression and Masking for Soccer Event Spotting","created":"2021-02-15","cited_by_count":19,"area":null},{"id":"2209.01425","title":"Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition","created":"2022-09-03","cited_by_count":17,"area":null},{"id":"2203.15336","title":"End-to-End Compressed Video Representation Learning for Generic Event Boundary Detection","created":"2022-03-29","cited_by_count":16,"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":"2211.06742","title":"Deep Unsupervised Key Frame Extraction for Efficient Video Classification","created":"2022-11-12","cited_by_count":14,"area":null},{"id":"2109.00953","title":"TrouSPI-Net: Spatio-temporal attention on parallel atrous convolutions and U-GRUs for skeletal pedestrian crossing prediction","created":"2021-09-02","cited_by_count":13,"area":null},{"id":"2110.14994","title":"Skeleton-Based Mutually Assisted Interacted Object Localization and Human Action Recognition","created":"2021-10-28","cited_by_count":13,"area":null},{"id":"2201.06268","title":"Continual Transformers: Redundancy-Free Attention for Online Inference","created":"2022-01-17","cited_by_count":12,"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":"2112.12668","title":"3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Na\\\"ive","created":"2021-12-23","cited_by_count":10,"area":null},{"id":"2504.00072","title":"Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs","created":"2025-03-31","cited_by_count":9,"area":null},{"id":"2203.01933","title":"Temporal Context Matters: Enhancing Single Image Prediction with Disease Progression Representations","created":"2022-03-02","cited_by_count":8,"area":null},{"id":"2208.03775","title":"Video-based Human Action Recognition using Deep Learning: A Review","created":"2022-08-07","cited_by_count":7,"area":null},{"id":"2208.07929","title":"ViT-ReT: Vision and Recurrent Transformer Neural Networks for Human Activity Recognition in Videos","created":"2022-08-16","cited_by_count":7,"area":null},{"id":"2106.10137","title":"Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting","created":"2021-06-18","cited_by_count":6,"area":null},{"id":"2203.08942","title":"ABN: Agent-Aware Boundary Networks for Temporal Action Proposal Generation","created":"2022-03-16","cited_by_count":6,"area":null},{"id":"2103.14785","title":"A Comprehensive Review of the Video-to-Text Problem","created":"2021-03-27","cited_by_count":5,"area":null},{"id":"2107.05122","title":"Interpretable Deep Feature Propagation for Early Action Recognition","created":"2021-07-11","cited_by_count":5,"area":null},{"id":"2111.13675","title":"Weakly-guided Self-supervised Pretraining for Temporal Activity Detection","created":"2021-11-26","cited_by_count":5,"area":null},{"id":"2201.04021","title":"Optimization Planning for 3D ConvNets","created":"2022-01-11","cited_by_count":5,"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":"2412.04189","title":"HANDI: Hand-Centric Text-and-Image Conditioned Video Generation","created":"2024-12-05","cited_by_count":5,"area":null},{"id":"2202.02314","title":"Towards To-a-T Spatio-Temporal Focus for Skeleton-Based Action Recognition","created":"2022-02-04","cited_by_count":4,"area":null},{"id":"2206.10491","title":"Bi-Calibration Networks for Weakly-Supervised Video Representation Learning","created":"2022-06-21","cited_by_count":4,"area":null},{"id":"2302.09187","title":"Video Action Recognition Collaborative Learning with Dynamics via PSO-ConvNet Transformer","created":"2023-02-17","cited_by_count":4,"area":null},{"id":"2308.04834","title":"View while Moving: Efficient Video Recognition in Long-untrimmed Videos","created":"2023-08-09","cited_by_count":4,"area":null},{"id":"2101.05490","title":"Neural networks behave as hash encoders: An empirical study","created":"2021-01-14","cited_by_count":3,"area":null},{"id":"2104.11520","title":"Modeling long-term interactions to enhance action recognition","created":"2021-04-23","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":"2303.16118","title":"CycleACR: Cycle Modeling of Actor-Context Relations for Video Action Detection","created":"2023-03-28","cited_by_count":3,"area":null},{"id":"2308.12447","title":"MOFO: MOtion FOcused Self-Supervision for Video Understanding","created":"2023-08-23","cited_by_count":3,"area":null},{"id":"2309.15431","title":"Local Compressed Video Stream Learning for Generic Event Boundary Detection","created":"2023-09-27","cited_by_count":3,"area":null},{"id":"2112.11384","title":"Sports Video: Fine-Grained Action Detection and Classification of Table Tennis Strokes from Videos for MediaEval 2021","created":"2021-12-16","cited_by_count":2,"area":null},{"id":"2208.01910","title":"Multimodal Generation of Novel Action Appearances for Synthetic-to-Real Recognition of Activities of Daily Living","created":"2022-08-03","cited_by_count":2,"area":null},{"id":"2211.04888","title":"Extending Temporal Data Augmentation for Video Action Recognition","created":"2022-11-09","cited_by_count":2,"area":null},{"id":"2301.13576","title":"Sport Task: Fine Grained Action Detection and Classification of Table Tennis Strokes from Videos for MediaEval 2022","created":"2023-01-31","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":"2501.07100","title":"Collaborative Learning for 3D Hand-Object Reconstruction and Compositional Action Recognition from Egocentric RGB Videos Using Superquadrics","created":"2025-01-13","cited_by_count":2,"area":null},{"id":"2602.23294","title":"Towards Long-Form Spatio-Temporal Video Grounding","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2102.01285","title":"GCF-Net: Gated Clip Fusion Network for Video Action Recognition","created":"2021-02-02","cited_by_count":1,"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":"2104.13051","title":"Three-stream network for enriched Action Recognition","created":"2021-04-27","cited_by_count":1,"area":null},{"id":"2108.03375","title":"Temporal Action Localization Using Gated Recurrent Units","created":"2021-08-07","cited_by_count":1,"area":null},{"id":"2110.05976","title":"Early Melanoma Diagnosis with Sequential Dermoscopic Images","created":"2021-10-12","cited_by_count":1,"area":null},{"id":"2112.09448","title":"Distillation of Human-Object Interaction Contexts for Action Recognition","created":"2021-12-17","cited_by_count":1,"area":null},{"id":"2203.06749","title":"Decontextualized I3D ConvNet for ultra-distance runners performance analysis at a glance","created":"2022-03-13","cited_by_count":1,"area":null},{"id":"2204.08460","title":"3D Convolutional Networks for Action Recognition: Application to Sport Gesture Recognition","created":"2022-04-13","cited_by_count":1,"area":null},{"id":"2208.05034","title":"Human Activity Recognition Using Cascaded Dual Attention CNN and Bi-Directional GRU Framework","created":"2022-08-09","cited_by_count":1,"area":null},{"id":"2209.11316","title":"FuTH-Net: Fusing Temporal Relations and Holistic Features for Aerial Video Classification","created":"2022-09-22","cited_by_count":1,"area":null},{"id":"2212.03384","title":"DroneAttention: Sparse Weighted Temporal Attention for Drone-Camera Based Activity Recognition","created":"2022-12-07","cited_by_count":1,"area":null},{"id":"2311.00800","title":"Beyond still images: Temporal features and input variance resilience","created":"2023-11-01","cited_by_count":1,"area":null},{"id":"2311.17942","title":"Object-based (yet Class-agnostic) Video Domain Adaptation","created":"2023-11-29","cited_by_count":1,"area":null},{"id":"2102.01441","title":"Face Recognition using 3D CNNs","created":"2021-02-02","cited_by_count":0,"area":null},{"id":"2103.10567","title":"CLTA: Contents and Length-based Temporal Attention for Few-shot Action Recognition","created":"2021-03-18","cited_by_count":0,"area":null},{"id":"2205.11232","title":"Deep Neural Network approaches for Analysing Videos of Music Performances","created":"2022-05-05","cited_by_count":0,"area":null},{"id":"2208.14847","title":"Attentive pooling for Group Activity Recognition","created":"2022-08-31","cited_by_count":0,"area":null},{"id":"2210.10247","title":"Performance of different machine learning methods on activity recognition and pose estimation datasets","created":"2022-10-19","cited_by_count":0,"area":null},{"id":"2303.00138","title":"Texture-Based Input Feature Selection for Action Recognition","created":"2023-02-28","cited_by_count":0,"area":null},{"id":"2311.12344","title":"Modality Mixer Exploiting Complementary Information for Multi-modal Action Recognition","created":"2023-11-21","cited_by_count":0,"area":null},{"id":"2407.16514","title":"Is 3D Convolution with 5D Tensors Really Necessary for Video Analysis?","created":"2024-07-23","cited_by_count":0,"area":null},{"id":"2502.07277","title":"Enhancing Video Understanding: Deep Neural Networks for Spatiotemporal Analysis","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2503.19668","title":"A multitask transformer to sign language translation using motion gesture primitives","created":"2025-03-25","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}],"next_cursor":null}