{"total":33,"rows":[{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2105.05226","title":"Home Action Genome: Cooperative Compositional Action Understanding","created":"2021-05-11","cited_by_count":53,"area":null},{"id":"2101.07253","title":"Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentation","created":"2021-01-18","cited_by_count":40,"area":null},{"id":"2109.02618","title":"Bridging the Gap between Events and Frames through Unsupervised Domain Adaptation","created":"2021-09-06","cited_by_count":37,"area":null},{"id":"2111.13424","title":"ContIG: Self-supervised Multimodal Contrastive Learning for Medical Imaging with Genetics","created":"2021-11-26","cited_by_count":36,"area":null},{"id":"2104.07917","title":"Hop-Count Based Self-Supervised Anomaly Detection on Attributed Networks","created":"2021-04-16","cited_by_count":31,"area":null},{"id":"2203.01265","title":"Self-supervised Transformer for Deepfake Detection","created":"2022-03-02","cited_by_count":22,"area":null},{"id":"2105.06463","title":"Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency","created":"2021-05-13","cited_by_count":19,"area":null},{"id":"2105.01646","title":"Motion-Augmented Self-Training for Video Recognition at Smaller Scale","created":"2021-05-04","cited_by_count":17,"area":null},{"id":"2209.04027","title":"Cross-Modal Knowledge Transfer Without Task-Relevant Source Data","created":"2022-09-08","cited_by_count":17,"area":null},{"id":"2405.09592","title":"A Survey of Generative Techniques for Spatial-Temporal Data Mining","created":"2024-05-15","cited_by_count":14,"area":null},{"id":"2104.14764","title":"CoCon: Cooperative-Contrastive Learning","created":"2021-04-30","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":"2106.09703","title":"MaCLR: Motion-aware Contrastive Learning of Representations for Videos","created":"2021-06-17","cited_by_count":10,"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":"2405.02288","title":"Prospective Role of Foundation Models in Advancing Autonomous Vehicles","created":"2023-12-08","cited_by_count":7,"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":"2209.07811","title":"Modeling Multiple Views via Implicitly Preserving Global Consistency and Local Complementarity","created":"2022-09-16","cited_by_count":5,"area":null},{"id":"2306.06010","title":"A Large-Scale Analysis on Self-Supervised Video Representation Learning","created":"2023-06-09","cited_by_count":5,"area":null},{"id":"2202.09545","title":"Going Deeper into Recognizing Actions in Dark Environments: A Comprehensive Benchmark Study","created":"2022-02-19","cited_by_count":4,"area":null},{"id":"2401.05014","title":"Source-Free Cross-Modal Knowledge Transfer by Unleashing the Potential of Task-Irrelevant Data","created":"2024-01-10","cited_by_count":4,"area":null},{"id":"2103.00787","title":"Self-Supervised Multi-View Learning via Auto-Encoding 3D Transformations","created":"2021-03-01","cited_by_count":3,"area":null},{"id":"2210.06297","title":"Multimodality Multi-Lead ECG Arrhythmia Classification using Self-Supervised Learning","created":"2022-09-30","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":"2601.03181","title":"Multi-Modal Data-Enhanced Foundation Models for Prediction and Control in Wireless Networks: A Survey","created":"2026-01-06","cited_by_count":3,"area":null},{"id":"2103.06032","title":"Cross-modal Image Retrieval with Deep Mutual Information Maximization","created":"2021-03-10","cited_by_count":2,"area":null},{"id":"2112.00804","title":"PreViTS: Contrastive Pretraining with Video Tracking Supervision","created":"2021-12-01","cited_by_count":2,"area":null},{"id":"2109.02344","title":"Information Theory-Guided Heuristic Progressive Multi-View Coding","created":"2021-09-06","cited_by_count":1,"area":null},{"id":"2108.03329","title":"Feature-Supervised Action Modality Transfer","created":"2021-08-06","cited_by_count":0,"area":null},{"id":"2110.11160","title":"Self-Supervised Visual Representation Learning Using Lightweight Architectures","created":"2021-10-21","cited_by_count":0,"area":null},{"id":"2211.13309","title":"How do Cross-View and Cross-Modal Alignment Affect Representations in Contrastive Learning?","created":"2022-11-23","cited_by_count":0,"area":null},{"id":"2305.11881","title":"Self-Supervised Learning for Point Clouds Data: A Survey","created":"2023-05-09","cited_by_count":0,"area":null},{"id":"2308.10522","title":"Information Theory-Guided Heuristic Progressive Multi-View Coding","created":"2023-08-21","cited_by_count":0,"area":null}],"next_cursor":null}