{"total":193,"rows":[{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863,"area":null},{"id":"2312.16084","title":"LangSplat: 3D Language Gaussian Splatting","created":"2023-12-26","cited_by_count":415,"area":null},{"id":"2310.11440","title":"EvalCrafter: Benchmarking and Evaluating Large Video Generation Models","created":"2023-10-17","cited_by_count":340,"area":null},{"id":"2309.03903","title":"Tracking Anything with Decoupled Video Segmentation","created":"2023-09-07","cited_by_count":197,"area":null},{"id":"2310.12982","title":"Putting the Object Back into Video Object Segmentation","created":"2023-10-19","cited_by_count":188,"area":null},{"id":"2312.00863","title":"EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything","created":"2023-12-01","cited_by_count":188,"area":null},{"id":"2508.10934","title":"ViPE: Video Pose Engine for 3D Geometric Perception","created":"2025-08-12","cited_by_count":170,"area":null},{"id":"2406.10324","title":"L4GM: Large 4D Gaussian Reconstruction Model","created":"2024-06-14","cited_by_count":144,"area":null},{"id":"2406.19389","title":"OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding","created":"2024-06-27","cited_by_count":127,"area":"lr"},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2308.07926","title":"CoDeF: Content Deformation Fields for Temporally Consistent Video Processing","created":"2023-08-15","cited_by_count":108,"area":null},{"id":"2307.04370","title":"Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A Survey","created":"2023-07-10","cited_by_count":103,"area":"driving"},{"id":"2307.01197","title":"Segment Anything Meets Point Tracking","created":"2023-07-03","cited_by_count":81,"area":null},{"id":"2309.04946","title":"Efficient Emotional Adaptation for Audio-Driven Talking-Head Generation","created":"2023-09-10","cited_by_count":81,"area":null},{"id":"2311.18448","title":"HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video","created":"2023-11-30","cited_by_count":78,"area":null},{"id":"2307.00855","title":"Review of Large Vision Models and Visual Prompt Engineering","created":"2023-07-03","cited_by_count":77,"area":null},{"id":"2401.02955","title":"Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively","created":"2024-01-05","cited_by_count":75,"area":null},{"id":"2401.10229","title":"OMG-Seg: Is One Model Good Enough For All Segmentation?","created":"2024-01-18","cited_by_count":75,"area":null},{"id":"2402.13255","title":"How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Survey","created":"2024-02-20","cited_by_count":72,"area":null},{"id":"2305.08196","title":"A Comprehensive Survey on Segment Anything Model for Vision and Beyond","created":"2023-05-14","cited_by_count":64,"area":null},{"id":"2312.03047","title":"MagicStick: Controllable Video Editing via Control Handle Transformations","created":"2023-12-05","cited_by_count":62,"area":null},{"id":"2401.08392","title":"DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)","created":"2024-01-16","cited_by_count":58,"area":"agents"},{"id":"2404.11613","title":"InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior","created":"2024-04-17","cited_by_count":56,"area":"diffusion"},{"id":"2309.09709","title":"CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation","created":"2023-09-18","cited_by_count":53,"area":null},{"id":"2402.01105","title":"A Survey for Foundation Models in Autonomous Driving","created":"2024-02-02","cited_by_count":52,"area":"driving"},{"id":"2403.08268","title":"Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts","created":"2024-03-13","cited_by_count":52,"area":null},{"id":"2506.05302","title":"Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos","created":"2025-06-05","cited_by_count":51,"area":null},{"id":"2406.04221","title":"Matching Anything by Segmenting Anything","created":"2024-06-06","cited_by_count":50,"area":null},{"id":"2502.17258","title":"VideoGrain: Modulating Space-Time Attention for Multi-grained Video Editing","created":"2025-02-24","cited_by_count":50,"area":"diffusion"},{"id":"2306.06211","title":"A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineering","created":"2023-05-12","cited_by_count":45,"area":null},{"id":"2407.07111","title":"Diffusion Model-Based Video Editing: A Survey","created":"2024-06-26","cited_by_count":44,"area":"diffusion"},{"id":"2404.07977","title":"Gaga: Group Any Gaussians via 3D-aware Memory Bank","created":"2024-04-11","cited_by_count":41,"area":null},{"id":"2306.04121","title":"Matte Anything: Interactive Natural Image Matting with Segment Anything Models","created":"2023-06-07","cited_by_count":39,"area":null},{"id":"2406.09627","title":"RobustSAM: Segment Anything Robustly on Degraded Images","created":"2024-06-13","cited_by_count":36,"area":null},{"id":"2408.12957","title":"Image Segmentation in Foundation Model Era: A Survey","created":"2024-08-23","cited_by_count":35,"area":"diffusion"},{"id":"2312.13789","title":"TinySAM: Pushing the Envelope for Efficient Segment Anything Model","created":"2023-12-21","cited_by_count":33,"area":"distill"},{"id":"2405.03144","title":"PTQ4SAM: Post-Training Quantization for Segment Anything","created":"2024-05-06","cited_by_count":32,"area":null},{"id":"2306.07713","title":"Robustness of SAM: Segment Anything Under Corruptions and Beyond","created":"2023-06-13","cited_by_count":31,"area":null},{"id":"2401.17904","title":"Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation","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":"2308.05737","title":"Follow Anything: Open-set detection, tracking, and following in real-time","created":"2023-08-10","cited_by_count":29,"area":null},{"id":"2401.07654","title":"Foundation Models for Biomedical Image Segmentation: A Survey","created":"2024-01-15","cited_by_count":28,"area":null},{"id":"2403.16370","title":"GoodSAM: Bridging Domain and Capacity Gaps via Segment Anything Model for Distortion-aware Panoramic Semantic Segmentation","created":"2024-03-25","cited_by_count":28,"area":null},{"id":"2307.00997","title":"RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation","created":"2023-07-03","cited_by_count":25,"area":null},{"id":"2411.07555","title":"GaussianCut: Interactive segmentation via graph cut for 3D Gaussian Splatting","created":"2024-11-12","cited_by_count":25,"area":null},{"id":"2407.14500","title":"ViLLa: Video Reasoning Segmentation with Large Language Model","created":"2024-07-18","cited_by_count":24,"area":"lr"},{"id":"2404.09857","title":"Empowering Embodied Visual Tracking with Visual Foundation Models and Offline RL","created":"2024-04-15","cited_by_count":23,"area":"offlinerl"},{"id":"2402.04648","title":"OV-NeRF: Open-vocabulary Neural Radiance Fields with Vision and Language Foundation Models for 3D Semantic Understanding","created":"2024-02-07","cited_by_count":22,"area":null},{"id":"2403.11694","title":"Object Segmentation-Assisted Inter Prediction for Versatile Video Coding","created":"2024-03-18","cited_by_count":22,"area":null},{"id":"2311.17338","title":"MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and Editing","created":"2023-11-29","cited_by_count":21,"area":"diffusion"},{"id":"2411.18933","title":"Efficient Track Anything","created":"2024-11-28","cited_by_count":21,"area":null},{"id":"2307.06526","title":"AvatarFusion: Zero-shot Generation of Clothing-Decoupled 3D Avatars Using 2D Diffusion","created":"2023-07-13","cited_by_count":20,"area":null},{"id":"2310.00132","title":"QDFormer: Towards Robust Audiovisual Segmentation in Complex Environments with Quantization-based Semantic Decomposition","created":"2023-09-29","cited_by_count":20,"area":null},{"id":"2502.06756","title":"SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2311.04414","title":"Learning the What and How of Annotation in Video Object Segmentation","created":"2023-11-08","cited_by_count":19,"area":null},{"id":"2408.15876","title":"Unleashing the Temporal-Spatial Reasoning Capacity of GPT for Training-Free Audio and Language Referenced Video Object Segmentation","created":"2024-08-28","cited_by_count":19,"area":"lr"},{"id":"2411.09921","title":"Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level","created":"2024-11-15","cited_by_count":19,"area":"lr"},{"id":"2307.12291","title":"TransHuman: A Transformer-based Human Representation for Generalizable Neural Human Rendering","created":"2023-07-23","cited_by_count":18,"area":null},{"id":"2405.19586","title":"SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation","created":"2024-05-30","cited_by_count":18,"area":null},{"id":"2408.16768","title":"SAM2Point: Segment Any 3D as Videos in Zero-shot and Promptable Manners","created":"2024-08-29","cited_by_count":18,"area":null},{"id":"2307.02427","title":"FOCUS: Object-Centric World Models for Robotics Manipulation","created":"2023-07-05","cited_by_count":17,"area":"wm"},{"id":"2403.16111","title":"EVA: Zero-shot Accurate Attributes and Multi-Object Video Editing","created":"2024-03-24","cited_by_count":17,"area":"diffusion"},{"id":"2409.00924","title":"MedSAM-U: Uncertainty-Guided Auto Multi-Prompt Adaptation for Reliable MedSAM","created":"2024-09-02","cited_by_count":17,"area":null},{"id":"2412.03347","title":"DIVE: Taming DINO for Subject-Driven Video Editing","created":"2024-12-04","cited_by_count":17,"area":"diffusion"},{"id":"2403.03270","title":"Bi-KVIL: Keypoints-based Visual Imitation Learning of Bimanual Manipulation Tasks","created":"2024-03-05","cited_by_count":16,"area":"offlinerl"},{"id":"2410.04960","title":"On Efficient Variants of Segment Anything Model: A Survey","created":"2024-10-07","cited_by_count":16,"area":null},{"id":"2310.10912","title":"Towards Training-free Open-world Segmentation via Image Prompt Foundation Models","created":"2023-10-17","cited_by_count":15,"area":null},{"id":"2504.12080","title":"DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistency","created":"2025-04-16","cited_by_count":15,"area":null},{"id":"2403.11427","title":"BAGS: Building Animatable Gaussian Splatting from a Monocular Video with Diffusion Priors","created":"2024-03-18","cited_by_count":14,"area":"diffusion"},{"id":"2310.16383","title":"Open-NeRF: Towards Open Vocabulary NeRF Decomposition","created":"2023-10-25","cited_by_count":13,"area":null},{"id":"2406.11210","title":"Zero-Shot Scene Change Detection","created":"2024-06-17","cited_by_count":13,"area":null},{"id":"2406.18115","title":"Open-vocabulary Mobile Manipulation in Unseen Dynamic Environments with 3D Semantic Maps","created":"2024-06-26","cited_by_count":13,"area":null},{"id":"2307.16377","title":"JOTR: 3D Joint Contrastive Learning with Transformers for Occluded Human Mesh Recovery","created":"2023-07-31","cited_by_count":12,"area":null},{"id":"2312.17116","title":"Generalizable Visual Reinforcement Learning with Segment Anything Model","created":"2023-12-28","cited_by_count":12,"area":null},{"id":"2403.16646","title":"Clustering Propagation for Universal Medical Image Segmentation","created":"2024-03-25","cited_by_count":12,"area":null},{"id":"2502.13078","title":"L4P: Towards Unified Low-Level 4D Vision Perception","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2407.05023","title":"SurgicalGaussian: Deformable 3D Gaussians for High-Fidelity Surgical Scene Reconstruction","created":"2024-07-06","cited_by_count":11,"area":null},{"id":"2408.09115","title":"GoodSAM++: Bridging Domain and Capacity Gaps via Segment Anything Model for Panoramic Semantic Segmentation","created":"2024-08-17","cited_by_count":11,"area":null},{"id":"2412.01826","title":"RELOCATE: A Simple Training-Free Baseline for Visual Query Localization Using Region-Based Representations","created":"2024-12-02","cited_by_count":11,"area":null},{"id":"2405.02004","title":"M${^2}$Depth: Self-supervised Two-Frame Multi-camera Metric Depth Estimation","created":"2024-05-03","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":"2403.09620","title":"PosSAM: Panoptic Open-vocabulary Segment Anything","created":"2024-03-14","cited_by_count":9,"area":null},{"id":"2405.02608","title":"UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model","created":"2024-05-04","cited_by_count":8,"area":null},{"id":"2406.15829","title":"MVOC: a training-free multiple video object composition method with diffusion models","created":"2024-06-22","cited_by_count":8,"area":"diffusion"},{"id":"2410.20927","title":"VLMimic: Vision Language Models are Visual Imitation Learner for Fine-grained Actions","created":"2024-10-28","cited_by_count":8,"area":"mllm"},{"id":"2506.01304","title":"SAM-I2V: Upgrading SAM to Support Promptable Video Segmentation with Less than 0.2% Training Cost","created":"2025-06-02","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":"2311.16635","title":"MotionZero:Exploiting Motion Priors for Zero-shot Text-to-Video Generation","created":"2023-11-28","cited_by_count":7,"area":null},{"id":"2405.15580","title":"Open-Vocabulary SAM3D: Towards Training-free Open-Vocabulary 3D Scene Understanding","created":"2024-05-24","cited_by_count":7,"area":null},{"id":"2406.03723","title":"Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-aware Spatio-Temporal Sampling","created":"2024-06-06","cited_by_count":7,"area":null},{"id":"2406.06523","title":"NaRCan: Natural Refined Canonical Image with Integration of Diffusion Prior for Video Editing","created":"2024-06-10","cited_by_count":7,"area":"diffusion"},{"id":"2408.02110","title":"AvatarPose: Avatar-guided 3D Pose Estimation of Close Human Interaction from Sparse Multi-view Videos","created":"2024-08-04","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":"2503.21246","title":"DynamiCtrl: Rethinking the Basic Structure and the Role of Text for High-quality Human Image Animation","created":"2025-03-27","cited_by_count":7,"area":"diffusion"},{"id":"2305.13093","title":"Restore Anything Pipeline: Segment Anything Meets Image Restoration","created":"2023-05-22","cited_by_count":6,"area":null},{"id":"2309.13772","title":"Motion Segmentation from a Moving Monocular Camera","created":"2023-09-24","cited_by_count":6,"area":null},{"id":"2311.00556","title":"ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab","created":"2023-11-01","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":"2407.16682","title":"SAM-CP: Marrying SAM with Composable Prompts for Versatile Segmentation","created":"2024-07-23","cited_by_count":6,"area":null}],"next_cursor":"100"}