{"total":51,"rows":[{"id":"2105.02668","title":"VideoLT: Large-scale Long-tailed Video Recognition","created":"2021-05-06","cited_by_count":35,"area":null},{"id":"2201.06494","title":"AugLy: Data Augmentations for Robustness","created":"2022-01-17","cited_by_count":34,"area":null},{"id":"2212.10888","title":"A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability","created":"2022-12-21","cited_by_count":31,"area":null},{"id":"2206.04790","title":"Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition","created":"2022-06-09","cited_by_count":27,"area":null},{"id":"2208.09913","title":"A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective","created":"2022-08-21","cited_by_count":27,"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":"2312.00333","title":"Green Edge AI: A Contemporary Survey","created":"2023-12-01","cited_by_count":25,"area":null},{"id":"2103.16565","title":"Learning Representational Invariances for Data-Efficient Action Recognition","created":"2021-03-30","cited_by_count":22,"area":null},{"id":"2112.03905","title":"ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpoints","created":"2021-12-07","cited_by_count":20,"area":null},{"id":"2208.02080","title":"A Feature-space Multimodal Data Augmentation Technique for Text-video Retrieval","created":"2022-08-03","cited_by_count":13,"area":null},{"id":"2308.11093","title":"Video OWL-ViT: Temporally-consistent open-world localization in video","created":"2023-08-22","cited_by_count":13,"area":null},{"id":"2403.20254","title":"Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions","created":"2024-03-29","cited_by_count":12,"area":null},{"id":"2206.15015","title":"Exploring Temporally Dynamic Data Augmentation for Video Recognition","created":"2022-06-30","cited_by_count":9,"area":null},{"id":"2211.09146","title":"A Unified Multimodal De- and Re-coupling Framework for RGB-D Motion Recognition","created":"2022-11-16","cited_by_count":9,"area":null},{"id":"2204.00239","title":"ObjectMix: Data Augmentation by Copy-Pasting Objects in Videos for Action Recognition","created":"2022-04-01","cited_by_count":7,"area":null},{"id":"2207.09925","title":"An Efficient Framework for Few-shot Skeleton-based Temporal Action Segmentation","created":"2022-07-20","cited_by_count":7,"area":null},{"id":"2101.08237","title":"An Empirical Study and Analysis on Open-Set Semi-Supervised Learning","created":"2021-01-19","cited_by_count":6,"area":null},{"id":"2411.14049","title":"Out-Of-Distribution Detection with Diversification (Provably)","created":"2024-11-21","cited_by_count":6,"area":null},{"id":"2311.06231","title":"Learning Human Action Recognition Representations Without Real Humans","created":"2023-11-10","cited_by_count":5,"area":null},{"id":"2502.00156","title":"ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2107.01469","title":"Scene-aware Learning Network for Radar Object Detection","created":"2021-07-03","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":"2210.12527","title":"Baby Physical Safety Monitoring in Smart Home Using Action Recognition System","created":"2022-10-22","cited_by_count":4,"area":null},{"id":"2211.01796","title":"Beyond Instance Discrimination: Relation-aware Contrastive Self-supervised Learning","created":"2022-11-02","cited_by_count":4,"area":null},{"id":"2409.17091","title":"Ctrl-GenAug: Controllable Generative Augmentation for Medical Sequence Classification","created":"2024-09-25","cited_by_count":4,"area":null},{"id":"2109.07951","title":"Overview of Tencent Multi-modal Ads Video Understanding Challenge","created":"2021-09-16","cited_by_count":3,"area":null},{"id":"2310.02876","title":"Hate Speech Detection in Limited Data Contexts using Synthetic Data Generation","created":"2023-10-04","cited_by_count":3,"area":null},{"id":"2310.14556","title":"S3Aug: Segmentation, Sampling, and Shift for Action Recognition","created":"2023-10-23","cited_by_count":3,"area":null},{"id":"2402.11538","title":"PASCL: Supervised Contrastive Learning with Perturbative Augmentation for Particle Decay Reconstruction","created":"2024-02-18","cited_by_count":3,"area":null},{"id":"2405.14506","title":"SIAVC: Semi-Supervised Framework for Industrial Accident Video Classification","created":"2024-05-23","cited_by_count":3,"area":null},{"id":"2302.12688","title":"Video4MRI: An Empirical Study on Brain Magnetic Resonance Image Analytics with CNN-based Video Classification Frameworks","created":"2023-02-24","cited_by_count":2,"area":null},{"id":"2309.08264","title":"Leveraging the Power of Data Augmentation for Transformer-based Tracking","created":"2023-09-15","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":"2403.09506","title":"Don't Judge by the Look: Towards Motion Coherent Video Representation","created":"2024-03-14","cited_by_count":2,"area":null},{"id":"2409.06665","title":"Data Collection-free Masked Video Modeling","created":"2024-09-10","cited_by_count":2,"area":null},{"id":"2505.19495","title":"The Role of Video Generation in Enhancing Data-Limited Action Understanding","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2307.09136","title":"The Effects of Mixed Sample Data Augmentation are Class Dependent","created":"2023-07-18","cited_by_count":1,"area":null},{"id":"2311.05168","title":"FireMatch: A Semi-Supervised Video Fire Detection Network Based on Consistency and Distribution Alignment","created":"2023-11-09","cited_by_count":1,"area":null},{"id":"2412.20816","title":"MomentMix Augmentation with Length-Aware DETR for Temporally Robust Moment Retrieval","created":"2024-12-30","cited_by_count":1,"area":null},{"id":"2505.20694","title":"Temporal Saliency-Guided Distillation: A Scalable Framework for Distilling Video Datasets","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2508.05829","title":"TSMS-SAM2: Multi-scale Temporal Sampling Augmentation and Memory-Splitting Pruning for Promptable Video Object Segmentation and Tracking in Surgical Scenarios","created":"2025-08-07","cited_by_count":1,"area":null},{"id":"2510.19622","title":"Augmenting Moment Retrieval: Zero-Dependency Two-Stage Learning","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2112.03906","title":"Cross-modal Manifold Cutmix for Self-supervised Video Representation Learning","created":"2021-12-07","cited_by_count":0,"area":null},{"id":"2212.00214","title":"Test-Time Mixup Augmentation for Data and Class-Specific Uncertainty Estimation in Deep Learning Image Classification","created":"2022-12-01","cited_by_count":0,"area":null},{"id":"2311.05371","title":"Training Robust Deep Physiological Measurement Models with Synthetic Video-based Data","created":"2023-11-09","cited_by_count":0,"area":null},{"id":"2312.07621","title":"Spatiotemporal Event Graphs for Dynamic Scene Understanding","created":"2023-12-11","cited_by_count":0,"area":null},{"id":"2401.17883","title":"Reimagining Reality: A Comprehensive Survey of Video Inpainting Techniques","created":"2024-01-31","cited_by_count":0,"area":null},{"id":"2410.13565","title":"SDI-Paste: Synthetic Dynamic Instance Copy-Paste for Video Instance Segmentation","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2507.00752","title":"Multi-Modal Graph Convolutional Network with Sinusoidal Encoding for Robust Human Action Segmentation","created":"2025-07-01","cited_by_count":0,"area":null},{"id":"2508.02981","title":"MoExDA: Domain Adaptation for Edge-based Action Recognition","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2609.24367","title":"TReViS: Temporal Repetition Structure Aware Video Synthesis for Self-supervised Repetitive Action Counting","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}