{"total":21,"rows":[{"id":"2405.16009","title":"Streaming Long Video Understanding with Large Language Models","created":"2024-05-25","cited_by_count":167,"area":null},{"id":"2411.04998","title":"HourVideo: 1-Hour Video-Language Understanding","created":"2024-11-07","cited_by_count":113,"area":null},{"id":"2306.16741","title":"Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train","created":"2023-06-29","cited_by_count":75,"area":null},{"id":"2308.04549","title":"Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation","created":"2023-08-08","cited_by_count":24,"area":null},{"id":"2308.09951","title":"Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videos","created":"2023-08-19","cited_by_count":20,"area":null},{"id":"2308.09245","title":"Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videos","created":"2023-08-18","cited_by_count":19,"area":null},{"id":"2311.17893","title":"Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation","created":"2023-11-29","cited_by_count":10,"area":null},{"id":"2407.06871","title":"Rethinking Image-to-Video Adaptation: An Object-centric Perspective","created":"2024-07-09","cited_by_count":8,"area":null},{"id":"2309.00297","title":"Fine-Grained Spatiotemporal Motion Alignment for Contrastive Video Representation Learning","created":"2023-09-01","cited_by_count":7,"area":null},{"id":"2312.00826","title":"DEVIAS: Learning Disentangled Video Representations of Action and Scene","created":"2023-11-30","cited_by_count":7,"area":null},{"id":"2305.12959","title":"Contrastive Predictive Autoencoders for Dynamic Point Cloud Self-Supervised Learning","created":"2023-05-22","cited_by_count":5,"area":null},{"id":"2303.09154","title":"Bayesian Generalization Error in Linear Neural Networks with Concept Bottleneck Structure and Multitask Formulation","created":"2023-03-16","cited_by_count":3,"area":null},{"id":"2503.24108","title":"PolypSegTrack: Unified Foundation Model for Colonoscopy Video Analysis","created":"2025-03-31","cited_by_count":3,"area":null},{"id":"2403.09206","title":"Upper Bound of Bayesian Generalization Error in Partial Concept Bottleneck Model (CBM): Partial CBM outperforms naive CBM","created":"2024-03-14","cited_by_count":1,"area":null},{"id":"2501.06059","title":"COMIX: Compositional Explanations using Prototypes","created":"2025-01-10","cited_by_count":1,"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},{"id":"2505.24690","title":"Learning reusable concepts across different egocentric video understanding tasks","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2506.01980","title":"Surgical Foundation Model Leveraging Compression and Entropy Maximization for Image-Guided Surgical Assistance","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2603.25778","title":"Focus-to-Perceive Representation Learning: A Cognition-Inspired Hierarchical Framework for Endoscopic Video Analysis","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2607.23503","title":"Impute On-Demand: Adaptive Correlated Time Series Imputation for Changing Environments","created":"2026-07-26","cited_by_count":0,"area":null}],"next_cursor":null}