{"total":17,"rows":[{"id":"2508.00265","title":"Multimodal Referring Segmentation: A Survey","created":"2025-08-01","cited_by_count":22,"area":null},{"id":"2410.23287","title":"ReferEverything: Towards Segmenting Everything We Can Speak of in Videos","created":"2024-10-30","cited_by_count":10,"area":null},{"id":"2410.18538","title":"SMITE: Segment Me In TimE","created":"2024-10-24","cited_by_count":7,"area":null},{"id":"2501.13667","title":"MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation","created":"2025-01-23","cited_by_count":7,"area":null},{"id":"2507.20740","title":"Implicit Counterfactual Learning for Audio-Visual Segmentation","created":"2025-07-28","cited_by_count":5,"area":null},{"id":"2510.08458","title":"SummDiff: Generative Modeling of Video Summarization with Diffusion","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2503.03492","title":"Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2606.09646","title":"How Do Video Foundation Models Encode Intuitive Physics? Probing Across Pretraining Paradigms","created":"2026-06-08","cited_by_count":3,"area":null},{"id":"2505.12606","title":"Diff-MM: Exploring Pre-trained Text-to-Image Generation Model for Unified Multi-modal Object Tracking","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2509.08908","title":"Diffusion-Based Action Recognition Generalizes to Untrained Domains","created":"2025-09-10","cited_by_count":2,"area":null},{"id":"2603.07758","title":"AR2-4FV: Anchored Referring and Re-identification for Long-Term Grounding in Fixed-View Videos","created":"2026-03-08","cited_by_count":1,"area":null},{"id":"2508.20547","title":"SPGrasp: Spatiotemporal Prompt-driven Grasp Synthesis in Dynamic Scenes","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2510.07319","title":"Temporal Prompting Matters: Rethinking Referring Video Object Segmentation","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2603.14300","title":"Show Me When and Where: Towards Referring Video Object Segmentation in the Wild","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2603.20887","title":"Scene Graph-guided SegCaptioning Transformer with Fine-grained Alignment for Controllable Video Segmentation and Captioning","created":"2026-03-21","cited_by_count":0,"area":null},{"id":"2605.02134","title":"Video Generation with Predictive Latents","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2607.24098","title":"ReflexTrack: A Feedback-Driven Agent for Training-Free Referring Video Object Segmentation","created":"2026-07-27","cited_by_count":0,"area":null}],"next_cursor":null}