{"total":17,"rows":[{"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":"2102.06191","title":"Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals","created":"2021-02-11","cited_by_count":190,"area":null},{"id":"2205.07839","title":"Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization","created":"2022-05-16","cited_by_count":150,"area":null},{"id":"2206.06363","title":"Discovering Object Masks with Transformers for Unsupervised Semantic Segmentation","created":"2022-06-13","cited_by_count":54,"area":null},{"id":"2111.06394","title":"The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos","created":"2021-11-11","cited_by_count":45,"area":null},{"id":"2411.10836","title":"AnimateAnything: Consistent and Controllable Animation for Video Generation","created":"2024-11-16","cited_by_count":35,"area":null},{"id":"2412.09349","title":"DisPose: Disentangling Pose Guidance for Controllable Human Image Animation","created":"2024-12-12","cited_by_count":35,"area":null},{"id":"2409.08857","title":"InstantDrag: Improving Interactivity in Drag-based Image Editing","created":"2024-09-13","cited_by_count":31,"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":"2204.11335","title":"Simulating Fluids in Real-World Still Images","created":"2022-04-24","cited_by_count":15,"area":null},{"id":"2107.11851","title":"Transcript to Video: Efficient Clip Sequencing from Texts","created":"2021-07-25","cited_by_count":13,"area":null},{"id":"2502.03207","title":"MotionAgent: Fine-grained Controllable Video Generation via Motion Field Agent","created":"2025-02-05","cited_by_count":11,"area":null},{"id":"2307.13640","title":"Optical Flow boosts Unsupervised Localization and Segmentation","created":"2023-07-25","cited_by_count":7,"area":null},{"id":"2506.11777","title":"Self-supervised Learning of Echocardiographic Video Representations via Online Cluster Distillation","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2410.09768","title":"Tokenizing Motion: A Generative Approach for Scene Dynamics Compression","created":"2024-10-13","cited_by_count":3,"area":null},{"id":"2409.15832","title":"Point-PNG: Conditional Pseudo-Negatives Generation for Point Cloud Pre-Training","created":"2024-09-24","cited_by_count":1,"area":null},{"id":"2403.06243","title":"BlazeBVD: Make Scale-Time Equalization Great Again for Blind Video Deflickering","created":"2024-03-10","cited_by_count":0,"area":null}],"next_cursor":null}