{"list":"other","total":63,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"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":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2203.17270","title":"BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers","created":"2022-03-31","cited_by_count":1218},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"1612.00603","title":"A Point Set Generation Network for 3D Object Reconstruction from a Single Image","created":"2016-12-02","cited_by_count":979},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"2311.16493","title":"Mip-Splatting: Alias-free 3D Gaussian Splatting","created":"2023-11-27","cited_by_count":667},{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503},{"id":"2312.16084","title":"LangSplat: 3D Language Gaussian Splatting","created":"2023-12-26","cited_by_count":415},{"id":"2302.07817","title":"Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction","created":"2023-02-15","cited_by_count":409},{"id":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382},{"id":"2306.01567","title":"Segment Anything in High Quality","created":"2023-06-02","cited_by_count":376},{"id":"2112.00726","title":"MonoScene: Monocular 3D Semantic Scene Completion","created":"2021-12-01","cited_by_count":363},{"id":"2312.07920","title":"DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes","created":"2023-12-13","cited_by_count":360},{"id":"2306.14289","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","created":"2023-06-25","cited_by_count":352},{"id":"2304.14365","title":"Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving","created":"2023-04-27","cited_by_count":332},{"id":"2303.09551","title":"SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving","created":"2023-03-16","cited_by_count":316},{"id":"2304.05316","title":"OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction","created":"2023-04-11","cited_by_count":293},{"id":"2306.12156","title":"Fast Segment Anything","created":"2023-06-21","cited_by_count":290},{"id":"2303.11301","title":"VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking","created":"2023-03-20","cited_by_count":222},{"id":"2303.03991","title":"OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception","created":"2023-03-07","cited_by_count":221},{"id":"2306.02851","title":"Scene as Occupancy","created":"2023-06-05","cited_by_count":209},{"id":"2206.00630","title":"Unifying Voxel-based Representation with Transformer for 3D Object Detection","created":"2022-06-01","cited_by_count":202},{"id":"2303.08131","title":"A Simple Framework for Open-Vocabulary Segmentation and Detection","created":"2023-03-14","cited_by_count":198},{"id":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166},{"id":"2307.01492","title":"FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation","created":"2023-07-04","cited_by_count":165},{"id":"2209.15639","title":"F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models","created":"2022-09-30","cited_by_count":150},{"id":"2311.12754","title":"SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction","created":"2023-11-21","cited_by_count":133},{"id":"2206.07959","title":"Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?","created":"2022-06-16","cited_by_count":128},{"id":"2309.09502","title":"RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision","created":"2023-09-18","cited_by_count":128},{"id":"2306.10013","title":"PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation","created":"2023-06-16","cited_by_count":115},{"id":"2008.09285","title":"Occupancy Anticipation for Efficient Exploration and Navigation","created":"2020-08-21","cited_by_count":106},{"id":"2311.12058","title":"FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugin","created":"2023-11-18","cited_by_count":103},{"id":"2105.09996","title":"VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding","created":"2021-05-20","cited_by_count":102},{"id":"2311.02873","title":"OVIR-3D: Open-Vocabulary 3D Instance Retrieval Without Training on 3D Data","created":"2023-11-06","cited_by_count":81},{"id":"2001.02192","title":"An Exploration of Embodied Visual Exploration","created":"2020-01-07","cited_by_count":58},{"id":"2409.12753","title":"DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input","created":"2024-09-19","cited_by_count":53},{"id":"2205.15938","title":"Voxel Field Fusion for 3D Object Detection","created":"2022-05-31","cited_by_count":50},{"id":"2408.11447","title":"GaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splatting","created":"2024-08-21","cited_by_count":50},{"id":"2112.01001","title":"SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency","created":"2021-12-02","cited_by_count":48},{"id":"2311.17707","title":"SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation","created":"2023-11-29","cited_by_count":44},{"id":"2301.12511","title":"Fast-BEV: A Fast and Strong Bird's-Eye View Perception Baseline","created":"2023-01-29","cited_by_count":40},{"id":"2306.02245","title":"SAM3D: Zero-Shot 3D Object Detection via Segment Anything Model","created":"2023-06-04","cited_by_count":40},{"id":"2407.04049","title":"Occupancy as Set of Points","created":"2024-07-04","cited_by_count":38},{"id":"2406.03175","title":"Dynamic 3D Gaussian Fields for Urban Areas","created":"2024-06-05","cited_by_count":35},{"id":"2108.07511","title":"LIF-Seg: LiDAR and Camera Image Fusion for 3D LiDAR Semantic Segmentation","created":"2021-08-17","cited_by_count":34},{"id":"2403.10191","title":"Generative Region-Language Pretraining for Open-Ended Object Detection","created":"2024-03-15","cited_by_count":29},{"id":"2306.09117","title":"UniOcc: Unifying Vision-Centric 3D Occupancy Prediction with Geometric and Semantic Rendering","created":"2023-06-15","cited_by_count":26},{"id":"2305.16133","title":"OVO: Open-Vocabulary Occupancy","created":"2023-05-25","cited_by_count":24},{"id":"2312.00703","title":"PointBeV: A Sparse Approach to BeV Predictions","created":"2023-12-01","cited_by_count":23},{"id":"2402.12792","title":"OccFlowNet: Towards Self-supervised Occupancy Estimation via Differentiable Rendering and Occupancy Flow","created":"2024-02-20","cited_by_count":22},{"id":"2407.12294","title":"VEON: Vocabulary-Enhanced Occupancy Prediction","created":"2024-07-17","cited_by_count":22},{"id":"2011.03981","title":"Learning-based 3D Occupancy Prediction for Autonomous Navigation in Occluded Environments","created":"2020-11-08","cited_by_count":21},{"id":"2407.17310","title":"LangOcc: Self-Supervised Open Vocabulary Occupancy Estimation via Volume Rendering","created":"2024-07-24","cited_by_count":16},{"id":"2410.05963","title":"Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts","created":"2024-10-08","cited_by_count":16}],"next_cursor":null}