{"total":17,"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":"2410.16268","title":"SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree","created":"2024-10-21","cited_by_count":80,"area":null},{"id":"2412.14295","title":"Temporally Consistent Object-Centric Learning by Contrasting Slots","created":"2024-12-18","cited_by_count":31,"area":null},{"id":"2507.15852","title":"Advancing Complex Video Object Segmentation via Progressive Concept Construction","created":"2025-07-21","cited_by_count":26,"area":null},{"id":"2508.01345","title":"Predicting Video Slot Attention Queries from Random Slot-Feature Pairs","created":"2025-08-02","cited_by_count":12,"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":"2404.15721","title":"SPARO: Selective Attention for Robust and Compositional Transformer Encodings for Vision","created":"2024-04-24","cited_by_count":4,"area":null},{"id":"2501.12477","title":"Slot-BERT: Self-supervised Object Discovery in Surgical Video","created":"2025-01-21","cited_by_count":4,"area":null},{"id":"2407.01726","title":"Grouped Discrete Representation Guides Object-Centric Learning","created":"2024-07-01","cited_by_count":2,"area":null},{"id":"2506.05543","title":"FRAME: Pre-Training Video Feature Representations via Anticipation and Memory","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2509.06165","title":"UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learning","created":"2025-09-07","cited_by_count":2,"area":null},{"id":"2605.03650","title":"Rethinking Temporal Consistency in Video Object-Centric Learning: From Prediction to Correspondence","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2509.02032","title":"ContextFusion and Bootstrap: An Effective Approach to Improve Slot Attention-Based Object-Centric Learning","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2603.17813","title":"M2P: Improving Visual Foundation Models with Mask-to-Point Weakly-Supervised Learning for Dense Point Tracking","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2607.07230","title":"`Attention-Guided Cross-Temporal Clustering for Self-Supervised Video Object Segmentation","created":"2026-07-08","cited_by_count":0,"area":null}],"next_cursor":null}