{"total":25,"rows":[{"id":"2503.21747","title":"CTRL-O: Language-Controllable Object-Centric Visual Representation Learning","created":"2025-03-27","cited_by_count":12,"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":"2505.20772","title":"MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learning","created":"2025-05-27","cited_by_count":11,"area":null},{"id":"2508.05417","title":"Smoothing Slot Attention Iterations and Recurrences","created":"2025-08-07","cited_by_count":6,"area":null},{"id":"2605.31033","title":"SlotMemory: Object-Centric KV Memory for Streaming Long-Video Generation","created":"2026-05-29","cited_by_count":6,"area":null},{"id":"2602.03390","title":"From Vicious to Virtuous Cycles: Synergistic Representation Learning for Unsupervised Video Object-Centric Learning","created":"2026-02-03","cited_by_count":5,"area":null},{"id":"2506.02964","title":"FORLA: Federated Object-centric Representation Learning with Slot Attention","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2603.22758","title":"Reconstruction-Guided Slot Curriculum: Addressing Object Over-Fragmentation in Video Object-Centric Learning","created":"2026-03-24","cited_by_count":3,"area":null},{"id":"2606.12601","title":"Dual-State Slot Attention: Decoupling Appearance and Identity for Video Object-Centric Learning","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2606.13714","title":"TSA: Temporal Slot Activation for Persistent Object-Centric Video Representation","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2606.15527","title":"Selective Synergistic Learning for Video Object-Centric Learning","created":"2026-06-14","cited_by_count":2,"area":null},{"id":"2606.23436","title":"Rethinking Object-Centric Representations for Video Dynamics Modeling","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2603.14022","title":"A Hyperbolic Perspective on Hierarchical Structure in Object-Centric Scene Representations","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2604.09045","title":"Scene-Agnostic Object-Centric Representation Learning for 3D Gaussian Splatting","created":"2026-04-10","cited_by_count":1,"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":"2607.09876","title":"Prompting-MammAlps: Fine-Grained Text-to-Video Retrieval for Camera-Trap Data","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2507.20855","title":"Compositional Video Synthesis by Temporal Object-Centric Learning","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2605.30211","title":"Cycle Consistency in Video Object-Centric Learning","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2605.31508","title":"Internalizing Temporal Consistency in Video Object-Centric Learning without Explicit Regularization","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.08249","title":"HSA: Hierarchical Slot Attention for Multi-granularity Scene-Decomposition","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.04866","title":"Persistent Object Narratives for Token-Efficient Video Language Models","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.06142","title":"Learning visual representations for compositional analysis of artworks and photographs","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.21636","title":"Semantic Slots for Video Object-Centric Learning","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2610.01201","title":"iSEE: Object Permanence Through Self-Supervision","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.20091","title":"RTAformer: Relation-Transition-Aware Transformer for Video Scene Graph Generation","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}