{"total":30,"rows":[{"id":"2503.23282","title":"AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos","created":"2025-03-30","cited_by_count":18,"area":null},{"id":"2408.00677","title":"Scaling Backwards: Minimal Synthetic Pre-training?","created":"2024-08-01","cited_by_count":14,"area":null},{"id":"2410.19635","title":"Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models","created":"2024-10-25","cited_by_count":13,"area":null},{"id":"2502.20985","title":"LesionLocator: Zero-Shot Universal Tumor Segmentation and Tracking in 3D Whole-Body Imaging","created":"2025-02-28","cited_by_count":12,"area":null},{"id":"2312.00598","title":"Learning from One Continuous Video Stream","created":"2023-12-01","cited_by_count":11,"area":null},{"id":"2408.11208","title":"PooDLe: Pooled and dense self-supervised learning from naturalistic videos","created":"2024-08-20","cited_by_count":11,"area":null},{"id":"2509.08502","title":"Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening","created":"2025-09-10","cited_by_count":11,"area":null},{"id":"2505.00209","title":"Direct Motion Models for Assessing Generated Videos","created":"2025-04-30","cited_by_count":10,"area":null},{"id":"2504.01961","title":"Learning from Streaming Video with Orthogonal Gradients","created":"2025-04-02","cited_by_count":9,"area":null},{"id":"2412.03215","title":"Beyond [cls]: Exploring the true potential of Masked Image Modeling representations","created":"2024-12-04","cited_by_count":6,"area":null},{"id":"2501.12254","title":"Memory Storyboard: Leveraging Temporal Segmentation for Streaming Self-Supervised Learning from Egocentric Videos","created":"2025-01-21","cited_by_count":6,"area":null},{"id":"2411.19941","title":"Perception Test 2024: Challenge Summary and a Novel Hour-Long VideoQA Benchmark","created":"2024-11-29","cited_by_count":5,"area":null},{"id":"2412.14294","title":"TRecViT: A Recurrent Video Transformer","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2506.08694","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","created":"2025-06-10","cited_by_count":5,"area":null},{"id":"2506.20057","title":"Universal pre-training by iterated random computation","created":"2025-06-24","cited_by_count":5,"area":null},{"id":"2409.15672","title":"Language-based Audio Moment Retrieval","created":"2024-09-24","cited_by_count":4,"area":null},{"id":"2509.10156","title":"LayerLock: Non-collapsing Representation Learning with Progressive Freezing","created":"2025-09-12","cited_by_count":4,"area":null},{"id":"2511.15131","title":"CASTELLA: Long Audio Dataset with Captions and Temporal Boundaries","created":"2025-11-19","cited_by_count":3,"area":null},{"id":"2608.27395","title":"LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics","created":"2026-08-27","cited_by_count":3,"area":null},{"id":"2510.05558","title":"Midway Network: Learning Representations for Recognition and Motion from Latent Dynamics","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2512.04085","title":"Unique Lives, Shared World: Learning from Single-Life Videos","created":"2025-12-03","cited_by_count":2,"area":null},{"id":"2501.02966","title":"Human Gaze Boosts Object-Centered Representation Learning","created":"2025-01-06","cited_by_count":1,"area":null},{"id":"2509.13846","title":"Consistent View Alignment Improves Foundation Models for 3D Medical Image Segmentation","created":"2025-09-17","cited_by_count":1,"area":null},{"id":"2602.04462","title":"Temporal Slowness in Central Vision Drives Semantic Object Learning","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.13912","title":"Towards Stable Self-Supervised Object Representations in Unconstrained Egocentric Video","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2603.29036","title":"Generating Humanless Environment Walkthroughs from Egocentric Walking Tour Videos","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.21502","title":"VFM$^{4}$SDG: Unveiling the Power of VFMs for Single-Domain Generalized Object Detection","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2604.26488","title":"Featurising Pixels from Dynamic 3D Scenes with Linear In-Context Learners","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2607.21576","title":"Self-Supervised Learning of Structured Dynamics from Videos","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2609.40333","title":"I Have a Stream: Making Self-Supervised Learning Work on Continuous Video","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}