{"total":173,"rows":[{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863,"area":null},{"id":"2312.00732","title":"Gaussian Grouping: Segment and Edit Anything in 3D Scenes","created":"2023-12-01","cited_by_count":393,"area":null},{"id":"2405.17421","title":"MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds","created":"2024-05-27","cited_by_count":179,"area":null},{"id":"2312.08168","title":"Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers","created":"2023-12-13","cited_by_count":175,"area":null},{"id":"2407.00634","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","created":"2024-06-30","cited_by_count":141,"area":null},{"id":"2402.01566","title":"Boximator: Generating Rich and Controllable Motions for Video Synthesis","created":"2024-02-02","cited_by_count":107,"area":null},{"id":"2411.11922","title":"SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory","created":"2024-11-18","cited_by_count":94,"area":null},{"id":"2403.15624","title":"Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting","created":"2024-03-22","cited_by_count":82,"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":"2407.17418","title":"3D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunities","created":"2024-07-24","cited_by_count":78,"area":null},{"id":"2508.05630","title":"MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes","created":"2025-08-07","cited_by_count":62,"area":null},{"id":"2407.11793","title":"Click-Gaussian: Interactive Segmentation to Any 3D Gaussians","created":"2024-07-16","cited_by_count":58,"area":null},{"id":"2409.08270","title":"FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally","created":"2024-09-12","cited_by_count":58,"area":null},{"id":"2411.02319","title":"GenXD: Generating Any 3D and 4D Scenes","created":"2024-11-04","cited_by_count":50,"area":null},{"id":"2404.19326","title":"LVOS: A Benchmark for Large-scale Long-term Video Object Segmentation","created":"2024-04-30","cited_by_count":44,"area":null},{"id":"2406.19353","title":"CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangement","created":"2024-06-27","cited_by_count":44,"area":null},{"id":"2410.13830","title":"DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control","created":"2024-10-17","cited_by_count":43,"area":null},{"id":"2404.07977","title":"Gaga: Group Any Gaussians via 3D-aware Memory Bank","created":"2024-04-11","cited_by_count":41,"area":null},{"id":"2408.11475","title":"TrackGo: A Flexible and Efficient Method for Controllable Video Generation","created":"2024-08-21","cited_by_count":39,"area":null},{"id":"2510.06219","title":"Human3R: Everyone Everywhere All at Once","created":"2025-10-07","cited_by_count":37,"area":null},{"id":"2407.10957","title":"Ref-AVS: Refer and Segment Objects in Audio-Visual Scenes","created":"2024-07-15","cited_by_count":33,"area":null},{"id":"2503.14029","title":"Rethinking End-to-End 2D to 3D Scene Segmentation in Gaussian Splatting","created":"2025-03-18","cited_by_count":31,"area":null},{"id":"2401.17857","title":"SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decomposition","created":"2024-01-31","cited_by_count":30,"area":null},{"id":"2404.12389","title":"Moving Object Segmentation: All You Need Is SAM (and Flow)","created":"2024-04-18","cited_by_count":30,"area":null},{"id":"2411.19083","title":"ObjectRelator: Enabling Cross-View Object Relation Understanding Across Ego-Centric and Exo-Centric Perspectives","created":"2024-11-28","cited_by_count":29,"area":null},{"id":"2501.02158","title":"Joint Optimization for 4D Human-Scene Reconstruction in the Wild","created":"2025-01-04","cited_by_count":29,"area":null},{"id":"2503.21761","title":"Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video","created":"2025-03-27","cited_by_count":29,"area":null},{"id":"2411.02394","title":"AutoVFX: Physically Realistic Video Editing from Natural Language Instructions","created":"2024-11-04","cited_by_count":27,"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":"2507.15454","title":"ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting","created":"2025-07-21","cited_by_count":25,"area":null},{"id":"2404.12379","title":"Dynamic Gaussians Mesh: Consistent Mesh Reconstruction from Dynamic Scenes","created":"2024-04-18","cited_by_count":22,"area":null},{"id":"2310.18709","title":"Audio-Visual Instance Segmentation","created":"2023-10-28","cited_by_count":21,"area":null},{"id":"2407.04504","title":"Segment Any 4D Gaussians","created":"2024-07-05","cited_by_count":20,"area":null},{"id":"2503.19443","title":"COB-GS: Clear Object Boundaries in 3DGS Segmentation Based on Boundary-Adaptive Gaussian Splitting","created":"2025-03-25","cited_by_count":19,"area":null},{"id":"2407.09473","title":"StyleSplat: 3D Object Style Transfer with Gaussian Splatting","created":"2024-07-12","cited_by_count":18,"area":null},{"id":"2412.08331","title":"SLGaussian: Fast Language Gaussian Splatting in Sparse Views","created":"2024-12-11","cited_by_count":18,"area":null},{"id":"2404.14249","title":"CLIP-GS: CLIP-Informed Gaussian Splatting for View-Consistent 3D Indoor Semantic Understanding","created":"2024-04-22","cited_by_count":16,"area":null},{"id":"2409.17523","title":"EAGLE: Egocentric AGgregated Language-video Engine","created":"2024-09-26","cited_by_count":16,"area":null},{"id":"2410.04960","title":"On Efficient Variants of Segment Anything Model: A Survey","created":"2024-10-07","cited_by_count":16,"area":null},{"id":"2410.17772","title":"Scaling Robot Policy Learning via Zero-Shot Labeling with Foundation Models","created":"2024-10-23","cited_by_count":14,"area":null},{"id":"2411.00639","title":"Event-guided Low-light Video Semantic Segmentation","created":"2024-11-01","cited_by_count":14,"area":null},{"id":"2411.14847","title":"Dynamics-Aware Gaussian Splatting Streaming Towards Fast On-the-Fly 4D Reconstruction","created":"2024-11-22","cited_by_count":14,"area":null},{"id":"2406.11210","title":"Zero-Shot Scene Change Detection","created":"2024-06-17","cited_by_count":13,"area":null},{"id":"2412.00155","title":"T-3DGS: Removing Transient Objects for 3D Scene Reconstruction","created":"2024-11-29","cited_by_count":13,"area":null},{"id":"2503.12781","title":"SAM2 for Image and Video Segmentation: A Comprehensive Survey","created":"2025-03-17","cited_by_count":13,"area":null},{"id":"2504.06978","title":"Wheat3DGS: In-field 3D Reconstruction, Instance Segmentation and Phenotyping of Wheat Heads with Gaussian Splatting","created":"2025-04-09","cited_by_count":13,"area":null},{"id":"2503.01646","title":"OpenGS-SLAM: Open-Set Dense Semantic SLAM with 3D Gaussian Splatting for Object-Level Scene Understanding","created":"2025-03-03","cited_by_count":12,"area":null},{"id":"2409.15959","title":"Semantics-Controlled Gaussian Splatting for Outdoor Scene Reconstruction and Rendering in Virtual Reality","created":"2024-09-24","cited_by_count":10,"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":"2412.16604","title":"OmniSplat: Taming Feed-Forward 3D Gaussian Splatting for Omnidirectional Images with Editable Capabilities","created":"2024-12-21","cited_by_count":10,"area":null},{"id":"2504.05541","title":"Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting","created":"2025-04-07","cited_by_count":10,"area":null},{"id":"2310.01946","title":"CoralVOS: Dataset and Benchmark for Coral Video Segmentation","created":"2023-10-03","cited_by_count":9,"area":null},{"id":"2401.05925","title":"Learning Segmented 3D Gaussians via Efficient Feature Unprojection for Zero-shot Neural Scene Segmentation","created":"2024-01-11","cited_by_count":9,"area":null},{"id":"2410.11187","title":"Multiview Scene Graph","created":"2024-10-15","cited_by_count":9,"area":null},{"id":"2402.16338","title":"BLO-SAM: Bi-level Optimization Based Overfitting-Preventing Finetuning of SAM","created":"2024-02-26","cited_by_count":8,"area":null},{"id":"2407.07402","title":"ActionVOS: Actions as Prompts for Video Object Segmentation","created":"2024-07-10","cited_by_count":8,"area":null},{"id":"2408.06975","title":"SpectralGaussians: Semantic, spectral 3D Gaussian splatting for multi-spectral scene representation, visualization and analysis","created":"2024-08-13","cited_by_count":8,"area":null},{"id":"2411.19290","title":"TRASE: Tracking-free 4D Segmentation and Editing","created":"2024-11-28","cited_by_count":8,"area":null},{"id":"2503.04034","title":"GaussianGraph: 3D Gaussian-based Scene Graph Generation for Open-world Scene Understanding","created":"2025-03-06","cited_by_count":8,"area":null},{"id":"2511.06457","title":"Inpaint360GS: Efficient Object-Aware 3D Inpainting via Gaussian Splatting for 360{\\deg} Scenes","created":"2025-11-09","cited_by_count":8,"area":null},{"id":"2403.08003","title":"Augmenting Efficient Real-time Surgical Instrument Segmentation in Video with Point Tracking and Segment Anything","created":"2024-03-12","cited_by_count":7,"area":null},{"id":"2407.07760","title":"Learning Spatial-Semantic Features for Robust Video Object Segmentation","created":"2024-07-10","cited_by_count":7,"area":null},{"id":"2411.02818","title":"LiVOS: Light Video Object Segmentation with Gated Linear Matching","created":"2024-11-05","cited_by_count":7,"area":null},{"id":"2502.16303","title":"Pointmap Association and Piecewise-Plane Constraint for Consistent and Compact 3D Gaussian Segmentation Field","created":"2025-02-22","cited_by_count":7,"area":null},{"id":"2403.04924","title":"$\\text{R}^2$-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations","created":"2024-03-07","cited_by_count":6,"area":null},{"id":"2407.01349","title":"PanopticRecon: Leverage Open-vocabulary Instance Segmentation for Zero-shot Panoptic Reconstruction","created":"2024-07-01","cited_by_count":6,"area":null},{"id":"2407.06540","title":"General and Task-Oriented Video Segmentation","created":"2024-07-09","cited_by_count":6,"area":null},{"id":"2506.01373","title":"No Train Yet Gain: Towards Generic Multi-Object Tracking in Sports and Beyond","created":"2025-06-02","cited_by_count":6,"area":null},{"id":"2510.18253","title":"OpenInsGaussian: Open-vocabulary Instance Gaussian Segmentation with Context-aware Cross-view Fusion","created":"2025-10-21","cited_by_count":6,"area":null},{"id":"2404.00650","title":"Deep Instruction Tuning for Segment Anything Model","created":"2024-03-31","cited_by_count":5,"area":null},{"id":"2408.08315","title":"Segment Anything for Videos: A Systematic Survey","created":"2024-07-31","cited_by_count":5,"area":null},{"id":"2408.09860","title":"3D-Aware Instance Segmentation and Tracking in Egocentric Videos","created":"2024-08-19","cited_by_count":5,"area":null},{"id":"2501.01119","title":"Leverage Cross-Attention for End-to-End Open-Vocabulary Panoptic Reconstruction","created":"2025-01-02","cited_by_count":5,"area":null},{"id":"2502.16941","title":"Gaussian Difference: Find Any Change Instance in 3D Scenes","created":"2025-02-24","cited_by_count":5,"area":null},{"id":"2505.01854","title":"Accelerating Volumetric Medical Image Annotation via Short-Long Memory SAM 2","created":"2025-05-03","cited_by_count":5,"area":null},{"id":"2512.05060","title":"4DLangVGGT: 4D Language-Visual Geometry Grounded Transformer","created":"2025-12-04","cited_by_count":5,"area":null},{"id":"2601.05738","title":"FeatureSLAM: Feature-enriched 3D gaussian splatting SLAM in real time","created":"2026-01-09","cited_by_count":5,"area":null},{"id":"2603.17840","title":"Video Understanding: From Geometry and Semantics to Unified Models","created":"2026-03-18","cited_by_count":5,"area":null},{"id":"2309.11077","title":"Weak Supervision for Label Efficient Visual Bug Detection","created":"2023-09-20","cited_by_count":4,"area":null},{"id":"2404.03657","title":"OW-VISCapTor: Abstractors for Open-World Video Instance Segmentation and Captioning","created":"2024-04-04","cited_by_count":4,"area":null},{"id":"2408.00169","title":"Strike the Balance: On-the-Fly Uncertainty based User Interactions for Long-Term Video Object Segmentation","created":"2024-07-31","cited_by_count":4,"area":null},{"id":"2409.16111","title":"CloudTrack: Scalable UAV Tracking with Cloud Semantics","created":"2024-09-24","cited_by_count":4,"area":null},{"id":"2410.07500","title":"Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy Labels","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2411.15193","title":"Gradient-Weighted Feature Back-Projection: A Fast Alternative to Feature Distillation in 3D Gaussian Splatting","created":"2024-11-19","cited_by_count":4,"area":null},{"id":"2411.19551","title":"Bootstraping Clustering of Gaussians for View-consistent 3D Scene Understanding","created":"2024-11-29","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":"2505.04861","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","created":"2025-05-08","cited_by_count":4,"area":null},{"id":"2505.20710","title":"Hierarchical Instruction-aware Embodied Visual Tracking","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2506.06846","title":"Multi-StyleGS: Stylizing Gaussian Splatting with Multiple Styles","created":"2025-06-07","cited_by_count":4,"area":null},{"id":"2508.01740","title":"AG$^2$aussian: Anchor-Graph Structured Gaussian Splatting for Instance-Level 3D Scene Understanding and Editing","created":"2025-08-03","cited_by_count":4,"area":null},{"id":"2511.15833","title":"EfficientSAM3: Progressive Hierarchical Distillation for Video Concept Segmentation from SAM1, 2, and 3","created":"2025-11-19","cited_by_count":4,"area":null},{"id":"2512.22745","title":"Split4D: Decomposed 4D Scene Reconstruction Without Video Segmentation","created":"2025-12-28","cited_by_count":4,"area":null},{"id":"2403.17937","title":"Efficient Video Object Segmentation via Modulated Cross-Attention Memory","created":"2024-03-26","cited_by_count":3,"area":null},{"id":"2404.15891","title":"OMEGAS: Object Mesh Extraction from Large Scenes Guided by Gaussian Segmentation","created":"2024-04-24","cited_by_count":3,"area":null},{"id":"2407.12121","title":"FoodMem: Near Real-time and Precise Food Video Segmentation","created":"2024-07-16","cited_by_count":3,"area":null},{"id":"2410.08781","title":"VideoSAM: Open-World Video Segmentation","created":"2024-10-11","cited_by_count":3,"area":null},{"id":"2503.11953","title":"SPOC: Spatially-Progressing Object State Change Segmentation in Video","created":"2025-03-15","cited_by_count":3,"area":null},{"id":"2506.02895","title":"VolTex: Food Volume Estimation using Text-Guided Segmentation and Neural Surface Reconstruction","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2508.19699","title":"LabelGS: Label-Aware 3D Gaussian Splatting for 3D Scene Segmentation","created":"2025-08-27","cited_by_count":3,"area":null},{"id":"2509.24563","title":"NeMo: Needle in a Montage for Video-Language Understanding","created":"2025-09-29","cited_by_count":3,"area":null}],"next_cursor":"100"}