{"list":"other","total":160,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2001.05566","title":"Image Segmentation Using Deep Learning: A Survey","created":"2020-01-15","cited_by_count":660},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615},{"id":"1912.12033","title":"Deep Learning for 3D Point Clouds: A Survey","created":"2019-12-27","cited_by_count":558},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2503.22020","title":"CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models","created":"2025-03-27","cited_by_count":451},{"id":"2312.16084","title":"LangSplat: 3D Language Gaussian Splatting","created":"2023-12-26","cited_by_count":415},{"id":"1606.05830","title":"Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age","created":"2016-06-19","cited_by_count":411},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370},{"id":"2408.08921","title":"Graph Retrieval-Augmented Generation: A Survey","created":"2024-08-15","cited_by_count":324},{"id":"2306.13631","title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","created":"2023-06-23","cited_by_count":289},{"id":"2405.14093","title":"A Survey on Vision-Language-Action Models for Embodied AI","created":"2024-05-23","cited_by_count":279},{"id":"2311.11700","title":"GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting","created":"2023-11-20","cited_by_count":278},{"id":"2412.03572","title":"Navigation World Models","created":"2024-12-04","cited_by_count":272},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261},{"id":"2004.10151","title":"Experience Grounds Language","created":"2020-04-21","cited_by_count":242},{"id":"2311.16038","title":"OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving","created":"2023-11-27","cited_by_count":233},{"id":"2311.18482","title":"Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding","created":"2023-11-30","cited_by_count":208},{"id":"2312.07531","title":"WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion","created":"2023-12-12","cited_by_count":206},{"id":"2312.03700","title":"OneLLM: One Framework to Align All Modalities with Language","created":"2023-12-06","cited_by_count":187},{"id":"2212.09802","title":"Panoptic Lifting for 3D Scene Understanding with Neural Fields","created":"2022-12-19","cited_by_count":174},{"id":"2307.10802","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","created":"2023-07-20","cited_by_count":136},{"id":"2311.12754","title":"SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction","created":"2023-11-21","cited_by_count":133},{"id":"2502.11079","title":"Phantom: Subject-consistent video generation via cross-modal alignment","created":"2025-02-16","cited_by_count":129},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124},{"id":"2312.10671","title":"Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance","created":"2023-12-17","cited_by_count":124},{"id":"2203.12667","title":"Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions","created":"2022-03-22","cited_by_count":117},{"id":"2306.10013","title":"PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation","created":"2023-06-16","cited_by_count":115},{"id":"2311.15537","title":"SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation","created":"2023-11-27","cited_by_count":97},{"id":"2401.18084","title":"Binding Touch to Everything: Learning Unified Multimodal Tactile Representations","created":"2024-01-31","cited_by_count":95},{"id":"2312.11557","title":"SAI3D: Segment Any Instance in 3D Scenes","created":"2023-12-17","cited_by_count":90},{"id":"2402.12259","title":"Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships","created":"2024-02-19","cited_by_count":80},{"id":"2407.17418","title":"3D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunities","created":"2024-07-24","cited_by_count":78},{"id":"2411.17040","title":"Multimodal Alignment and Fusion: A Survey","created":"2024-11-26","cited_by_count":74},{"id":"2201.00443","title":"Scene Graph Generation: A Comprehensive Survey","created":"2022-01-03","cited_by_count":73},{"id":"2510.16732","title":"A Comprehensive Survey on World Models for Embodied AI","created":"2025-10-19","cited_by_count":68},{"id":"2412.10373","title":"GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction","created":"2024-12-13","cited_by_count":67},{"id":"2202.02980","title":"3D Object Detection from Images for Autonomous Driving: A Survey","created":"2022-02-07","cited_by_count":66},{"id":"2501.02973","title":"HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos","created":"2025-01-06","cited_by_count":66},{"id":"2311.11016","title":"SNI-SLAM: Semantic Neural Implicit SLAM","created":"2023-11-18","cited_by_count":65},{"id":"2311.15851","title":"Single-Model and Any-Modality for Video Object Tracking","created":"2023-11-27","cited_by_count":65},{"id":"2403.12550","title":"RGBD GS-ICP SLAM","created":"2024-03-19","cited_by_count":65},{"id":"2312.17118","title":"Fully Sparse 3D Occupancy Prediction","created":"2023-12-28","cited_by_count":64},{"id":"2312.09866","title":"PLGSLAM: Progressive Neural Scene Represenation with Local to Global Bundle Adjustment","created":"2023-12-15","cited_by_count":63},{"id":"2403.14158","title":"Volumetric Environment Representation for Vision-Language Navigation","created":"2024-03-21","cited_by_count":63},{"id":"2403.16095","title":"CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-aware 3D Gaussian Field","created":"2024-03-24","cited_by_count":61},{"id":"2409.08270","title":"FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally","created":"2024-09-12","cited_by_count":58},{"id":"2410.03665","title":"Estimating Body and Hand Motion in an Ego-sensed World","created":"2024-10-04","cited_by_count":58},{"id":"2101.00443","title":"Semantics for Robotic Mapping, Perception and Interaction: A Survey","created":"2021-01-02","cited_by_count":56},{"id":"2401.07745","title":"MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation","created":"2024-01-15","cited_by_count":56},{"id":"2503.19199","title":"Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces","created":"2025-03-24","cited_by_count":54},{"id":"2601.03515","title":"Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents","created":"2026-01-07","cited_by_count":54},{"id":"2503.18052","title":"SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining","created":"2025-03-23","cited_by_count":52},{"id":"2504.03886","title":"WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments","created":"2025-04-04","cited_by_count":50},{"id":"2402.09944","title":"Loopy-SLAM: Dense Neural SLAM with Loop Closures","created":"2024-02-14","cited_by_count":48},{"id":"2312.02158","title":"PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness","created":"2023-12-04","cited_by_count":42},{"id":"2401.00789","title":"Retrieval-Augmented Egocentric Video Captioning","created":"2024-01-01","cited_by_count":42},{"id":"2503.12769","title":"ViSpeak: Visual Instruction Feedback in Streaming Videos","created":"2025-03-17","cited_by_count":42},{"id":"2407.11895","title":"OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces","created":"2024-07-16","cited_by_count":39},{"id":"2410.18084","title":"DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes","created":"2024-10-23","cited_by_count":38},{"id":"2412.17007","title":"Where am I? Cross-View Geo-localization with Natural Language Descriptions","created":"2024-12-22","cited_by_count":38},{"id":"2412.03142","title":"AffordDP: Generalizable Diffusion Policy with Transferable Affordance","created":"2024-12-04","cited_by_count":37},{"id":"2406.09829","title":"Open-Vocabulary Semantic Segmentation with Image Embedding Balancing","created":"2024-06-14","cited_by_count":35},{"id":"2411.18894","title":"T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Driving","created":"2024-11-28","cited_by_count":35},{"id":"2503.13446","title":"MoManipVLA: Transferring Vision-language-action Models for General Mobile Manipulation","created":"2025-03-17","cited_by_count":34},{"id":"2403.11848","title":"GraphBEV: Towards Robust BEV Feature Alignment for Multi-Modal 3D Object Detection","created":"2024-03-18","cited_by_count":33},{"id":"2407.10957","title":"Ref-AVS: Refer and Segment Objects in Audio-Visual Scenes","created":"2024-07-15","cited_by_count":33},{"id":"2505.04410","title":"DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception","created":"2025-05-07","cited_by_count":33},{"id":"2403.06351","title":"Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videos","created":"2024-03-11","cited_by_count":32},{"id":"2311.10988","title":"Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and Retention","created":"2023-11-18","cited_by_count":29},{"id":"2404.00469","title":"SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs","created":"2024-03-30","cited_by_count":29},{"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},{"id":"2502.07309","title":"Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Driving","created":"2025-02-11","cited_by_count":29},{"id":"2403.11074","title":"Audio-Visual Segmentation via Unlabeled Frame Exploitation","created":"2024-03-17","cited_by_count":28},{"id":"2411.19626","title":"GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding","created":"2024-11-29","cited_by_count":28},{"id":"2402.18115","title":"UniVS: Unified and Universal Video Segmentation with Prompts as Queries","created":"2024-02-28","cited_by_count":27},{"id":"2412.10402","title":"TANGO: Training-free Embodied AI Agents for Open-world Tasks","created":"2024-12-05","cited_by_count":27},{"id":"2412.18450","title":"3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding","created":"2024-12-24","cited_by_count":27},{"id":"2405.04534","title":"Tactile-Augmented Radiance Fields","created":"2024-05-07","cited_by_count":26},{"id":"2406.06948","title":"Neural Visibility Field for Uncertainty-Driven Active Mapping","created":"2024-06-11","cited_by_count":26},{"id":"2411.11278","title":"Towards Open-Vocabulary Audio-Visual Event Localization","created":"2024-11-18","cited_by_count":26},{"id":"2409.13430","title":"CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy Prediction","created":"2024-09-20","cited_by_count":24},{"id":"2312.08367","title":"ViLA: Efficient Video-Language Alignment for Video Question Answering","created":"2023-12-13","cited_by_count":23},{"id":"2405.16925","title":"OED: Towards One-stage End-to-End Dynamic Scene Graph Generation","created":"2024-05-27","cited_by_count":23}],"next_cursor":"100"}