{"total":39,"rows":[{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2105.14517","title":"GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning","created":"2021-05-30","cited_by_count":228,"area":null},{"id":"2301.05712","title":"A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends","created":"2023-01-13","cited_by_count":207,"area":null},{"id":"2106.15147","title":"SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption","created":"2021-06-29","cited_by_count":156,"area":null},{"id":"2101.07974","title":"TCLR: Temporal Contrastive Learning for Video Representation","created":"2021-01-20","cited_by_count":136,"area":null},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85,"area":null},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76,"area":null},{"id":"2207.10172","title":"Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzles","created":"2022-07-20","cited_by_count":62,"area":null},{"id":"2301.02074","title":"Test of Time: Instilling Video-Language Models with a Sense of Time","created":"2023-01-05","cited_by_count":51,"area":null},{"id":"2207.00449","title":"Dissecting Self-Supervised Learning Methods for Surgical Computer Vision","created":"2022-07-01","cited_by_count":48,"area":null},{"id":"2105.05217","title":"Representation Learning via Global Temporal Alignment and Cycle-Consistency","created":"2021-05-11","cited_by_count":44,"area":null},{"id":"2207.07611","title":"Position Prediction as an Effective Pretraining Strategy","created":"2022-07-15","cited_by_count":24,"area":null},{"id":"2203.14221","title":"How Severe is Benchmark-Sensitivity in Video Self-Supervised Learning?","created":"2022-03-27","cited_by_count":23,"area":null},{"id":"2112.05883","title":"Self-supervised Spatiotemporal Representation Learning by Exploiting Video Continuity","created":"2021-12-11","cited_by_count":22,"area":null},{"id":"2201.02494","title":"Progressive Video Summarization via Multimodal Self-supervised Learning","created":"2022-01-07","cited_by_count":21,"area":null},{"id":"2111.11051","title":"Contrast-reconstruction Representation Learning for Self-supervised Skeleton-based Action Recognition","created":"2021-11-22","cited_by_count":19,"area":null},{"id":"2208.06105","title":"Motion Sensitive Contrastive Learning for Self-supervised Video Representation","created":"2022-08-12","cited_by_count":11,"area":null},{"id":"2404.04452","title":"Vision transformers in domain adaptation and domain generalization: a study of robustness","created":"2024-04-05","cited_by_count":11,"area":null},{"id":"2201.05905","title":"SS-3DCapsNet: Self-supervised 3D Capsule Networks for Medical Segmentation on Less Labeled Data","created":"2022-01-15","cited_by_count":10,"area":null},{"id":"2211.11116","title":"Structure-Encoding Auxiliary Tasks for Improved Visual Representation in Vision-and-Language Navigation","created":"2022-11-20","cited_by_count":9,"area":null},{"id":"2302.09043","title":"Self-Supervised Representation Learning from Temporal Ordering of Automated Driving Sequences","created":"2023-02-17","cited_by_count":9,"area":null},{"id":"2504.00527","title":"SMILE: Infusing Spatial and Motion Semantics in Masked Video Learning","created":"2025-04-01","cited_by_count":9,"area":null},{"id":"2111.05329","title":"Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity","created":"2021-11-09","cited_by_count":8,"area":null},{"id":"2209.12074","title":"Self-supervised Learning for Unintentional Action Prediction","created":"2022-09-24","cited_by_count":7,"area":null},{"id":"2401.15900","title":"MV2MAE: Multi-View Video Masked Autoencoders","created":"2024-01-29","cited_by_count":6,"area":null},{"id":"2102.10378","title":"Self-Supervised Learning via multi-Transformation Classification for Action Recognition","created":"2021-02-20","cited_by_count":5,"area":null},{"id":"2209.10901","title":"Pretraining the Vision Transformer using self-supervised methods for vision based Deep Reinforcement Learning","created":"2022-09-22","cited_by_count":5,"area":null},{"id":"2312.13714","title":"Bootstrap Masked Visual Modeling via Hard Patches Mining","created":"2023-12-21","cited_by_count":5,"area":null},{"id":"2504.05706","title":"SEVERE++: Evaluating Benchmark Sensitivity in Generalization of Video Representation Learning","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2409.02371","title":"Unfolding Videos Dynamics via Taylor Expansion","created":"2024-09-04","cited_by_count":3,"area":null},{"id":"2504.06153","title":"A Large-Scale Analysis on Contextual Self-Supervised Video Representation Learning","created":"2025-04-08","cited_by_count":3,"area":null},{"id":"2203.15082","title":"Iterative, Deep Synthetic Aperture Sonar Image Segmentation","created":"2022-03-28","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":"2106.04921","title":"Self-supervised Feature Enhancement: Applying Internal Pretext Task to Supervised Learning","created":"2021-06-09","cited_by_count":1,"area":null},{"id":"2106.04922","title":"Self-supervision of Feature Transformation for Further Improving Supervised Learning","created":"2021-06-09","cited_by_count":1,"area":null},{"id":"2111.12664","title":"MIO : Mutual Information Optimization using Self-Supervised Binary Contrastive Learning","created":"2021-11-24","cited_by_count":1,"area":null},{"id":"2104.10481","title":"SKID: Self-Supervised Learning for Knee Injury Diagnosis from MRI Data","created":"2021-04-21","cited_by_count":0,"area":null},{"id":"2401.07584","title":"Collaboratively Self-supervised Video Representation Learning for Action Recognition","created":"2024-01-15","cited_by_count":0,"area":null},{"id":"2407.14069","title":"Self-Supervised Video Representation Learning in a Heuristic Decoupled Perspective","created":"2024-07-19","cited_by_count":0,"area":null}],"next_cursor":null}