{"total":31,"rows":[{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576,"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":"2207.10213","title":"Spotting Temporally Precise, Fine-Grained Events in Video","created":"2022-07-20","cited_by_count":40,"area":null},{"id":"2201.06494","title":"AugLy: Data Augmentations for Robustness","created":"2022-01-17","cited_by_count":34,"area":null},{"id":"2203.09978","title":"WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series","created":"2022-03-18","cited_by_count":30,"area":null},{"id":"2206.02002","title":"CVNets: High Performance Library for Computer Vision","created":"2022-06-04","cited_by_count":16,"area":null},{"id":"2311.17948","title":"Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenes","created":"2023-11-29","cited_by_count":12,"area":null},{"id":"2306.15742","title":"Differentially Private Video Activity Recognition","created":"2023-06-27","cited_by_count":9,"area":null},{"id":"2411.16718","title":"Neuro-Symbolic Evaluation of Text-to-Video Models using Formal Verification","created":"2024-11-22","cited_by_count":9,"area":null},{"id":"2202.13403","title":"A Multimodal German Dataset for Automatic Lip Reading Systems and Transfer Learning","created":"2022-02-27","cited_by_count":8,"area":null},{"id":"2203.08674","title":"Know your sensORs -- A Modality Study For Surgical Action Classification","created":"2022-03-16","cited_by_count":6,"area":null},{"id":"2306.03381","title":"VR.net: A Real-world Dataset for Virtual Reality Motion Sickness Research","created":"2023-06-06","cited_by_count":6,"area":null},{"id":"2211.00794","title":"Impact of annotation modality on label quality and model performance in the automatic assessment of laughter in-the-wild","created":"2022-11-02","cited_by_count":4,"area":null},{"id":"2411.05636","title":"Video RWKV:Video Action Recognition Based RWKV","created":"2024-11-08","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":"2504.09844","title":"MegaScale-Data: Scaling Dataloader for Multisource Large Foundation Model Training","created":"2025-04-14","cited_by_count":4,"area":null},{"id":"2204.07270","title":"Model-agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition","created":"2022-04-15","cited_by_count":3,"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":"2303.04068","title":"VOCALExplore: Pay-as-You-Go Video Data Exploration and Model Building [Technical Report]","created":"2023-03-07","cited_by_count":2,"area":null},{"id":"2308.16215","title":"Deep Video Codec Control for Vision Models","created":"2023-08-30","cited_by_count":2,"area":null},{"id":"2506.09411","title":"Synthetic Human Action Video Data Generation with Pose Transfer","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2401.01813","title":"Signal Processing in the Retina: Interpretable Graph Classifier to Predict Ganglion Cell Responses","created":"2024-01-03","cited_by_count":1,"area":null},{"id":"2403.01229","title":"REWIND Dataset: Privacy-preserving Speaking Status Segmentation from Multimodal Body Movement Signals in the Wild","created":"2024-03-02","cited_by_count":1,"area":null},{"id":"2505.13784","title":"Transfer Learning from Visual Speech Recognition to Mouthing Recognition in German Sign Language","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2507.20884","title":"The Importance of Facial Features in Vision-based Sign Language Recognition: Eyes, Mouth or Full Face?","created":"2025-07-28","cited_by_count":1,"area":null},{"id":"2406.06703","title":"Video-based Exercise Classification and Activated Muscle Group Prediction with Hybrid X3D-SlowFast Network","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2412.01525","title":"Towards Clinical Practice in CT-Based Pulmonary Disease Screening: An Efficient and Reliable Framework","created":"2024-12-02","cited_by_count":0,"area":null},{"id":"2503.12678","title":"Domain Generalization for Improved Human Activity Recognition in Office Space Videos Using Adaptive Pre-processing","created":"2025-03-16","cited_by_count":0,"area":null},{"id":"2505.24375","title":"Spatiotemporal Analysis of Forest Machine Operations Using 3D Video Classification","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2601.21673","title":"Multimodal Visual Surrogate Compression for Alzheimer's Disease Classification","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2609.24127","title":"Action-Slot: Structured Action-Centric Representation Learning for Multi-Agent Atomic Activity Understanding","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}