{"list":"other","total":69,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"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":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1406.2283","title":"Depth Map Prediction from a Single Image using a Multi-Scale Deep Network","created":"2014-06-09","cited_by_count":1274},{"id":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"1611.07759","title":"Multi-View 3D Object Detection Network for Autonomous Driving","created":"2016-11-23","cited_by_count":724},{"id":"2301.00493","title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","created":"2023-01-02","cited_by_count":707},{"id":"2401.02954","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","created":"2024-01-05","cited_by_count":642},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"2312.14150","title":"DriveLM: Driving with Graph Visual Question Answering","created":"2023-12-21","cited_by_count":536},{"id":"2306.16927","title":"End-to-end Autonomous Driving: Challenges and Frontiers","created":"2023-06-29","cited_by_count":490},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"id":"2104.10956","title":"FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection","created":"2021-04-22","cited_by_count":447},{"id":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404},{"id":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382},{"id":"2307.10984","title":"Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image","created":"2023-07-20","cited_by_count":365},{"id":"2205.13790","title":"BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework","created":"2022-05-27","cited_by_count":336},{"id":"2310.02601","title":"MagicDrive: Street View Generation with Diverse 3D Geometry Control","created":"2023-10-04","cited_by_count":252},{"id":"2305.03048","title":"Personalize Segment Anything Model with One Shot","created":"2023-05-04","cited_by_count":250},{"id":"2101.06806","title":"MP3: A Unified Model to Map, Perceive, Predict and Plan","created":"2021-01-18","cited_by_count":212},{"id":"2311.18651","title":"LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning","created":"2023-11-30","cited_by_count":210},{"id":"2002.10111","title":"SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation","created":"2020-02-24","cited_by_count":204},{"id":"1612.02401","title":"DeMoN: Depth and Motion Network for Learning Monocular Stereo","created":"2016-12-07","cited_by_count":201},{"id":"2309.00615","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","created":"2023-09-01","cited_by_count":194},{"id":"2004.06320","title":"A2D2: Audi Autonomous Driving Dataset","created":"2020-04-14","cited_by_count":190},{"id":"1908.06109","title":"RIO: 3D Object Instance Re-Localization in Changing Indoor Environments","created":"2019-08-16","cited_by_count":188},{"id":"2002.12212","title":"Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image","created":"2020-02-27","cited_by_count":172},{"id":"2211.10581","title":"Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusion","created":"2022-11-19","cited_by_count":162},{"id":"2207.10660","title":"Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild","created":"2022-07-21","cited_by_count":160},{"id":"2106.01178","title":"ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection","created":"2021-06-02","cited_by_count":157},{"id":"2012.09988","title":"Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations","created":"2020-12-18","cited_by_count":155},{"id":"2312.16170","title":"EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI","created":"2023-12-26","cited_by_count":147},{"id":"1805.01328","title":"Evaluation of CNN-based Single-Image Depth Estimation Methods","created":"2018-05-03","cited_by_count":138},{"id":"2206.09474","title":"3D Object Detection for Autonomous Driving: A Comprehensive Survey","created":"2022-06-19","cited_by_count":132},{"id":"2501.13926","title":"Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step","created":"2025-01-23","cited_by_count":131},{"id":"2407.08739","title":"MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine","created":"2024-07-11","cited_by_count":113},{"id":"2501.01428","title":"GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models","created":"2025-01-02","cited_by_count":109},{"id":"1903.10955","title":"GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving","created":"2019-03-26","cited_by_count":106},{"id":"2502.12894","title":"CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image","created":"2025-02-18","cited_by_count":106},{"id":"2203.13310","title":"MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection","created":"2022-03-24","cited_by_count":86},{"id":"2405.14475","title":"MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes","created":"2024-05-23","cited_by_count":71},{"id":"2405.11442","title":"Unifying 3D Vision-Language Understanding via Promptable Queries","created":"2024-05-19","cited_by_count":70},{"id":"2202.02980","title":"3D Object Detection from Images for Autonomous Driving: A Survey","created":"2022-02-07","cited_by_count":66},{"id":"2310.08586","title":"PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm","created":"2023-10-12","cited_by_count":56},{"id":"2410.09049","title":"SceneCraft: Layout-Guided 3D Scene Generation","created":"2024-10-11","cited_by_count":41},{"id":"2006.07864","title":"Cityscapes 3D: Dataset and Benchmark for 9 DoF Vehicle Detection","created":"2020-06-14","cited_by_count":39},{"id":"2406.07221","title":"Open-World Human-Object Interaction Detection via Multi-modal Prompts","created":"2024-06-11","cited_by_count":28},{"id":"2310.05699","title":"Uni3DETR: Unified 3D Detection Transformer","created":"2023-10-09","cited_by_count":27},{"id":"2411.16833","title":"Open Vocabulary Monocular 3D Object Detection","created":"2024-11-25","cited_by_count":23},{"id":"2409.04234","title":"UniDet3D: Multi-dataset Indoor 3D Object Detection","created":"2024-09-06","cited_by_count":20},{"id":"2403.19580","title":"OV-Uni3DETR: Towards Unified Open-Vocabulary 3D Object Detection via Cycle-Modality Propagation","created":"2024-03-28","cited_by_count":19},{"id":"2408.16768","title":"SAM2Point: Segment Any 3D as Videos in Zero-shot and Promptable Manners","created":"2024-08-29","cited_by_count":18},{"id":"2410.10799","title":"Towards Foundation Models for 3D Vision: How Close Are We?","created":"2024-10-14","cited_by_count":13},{"id":"2405.15619","title":"DiffCalib: Reformulating Monocular Camera Calibration as Diffusion-Based Dense Incident Map Generation","created":"2024-05-24","cited_by_count":9},{"id":"2412.11412","title":"V-MIND: Building Versatile Monocular Indoor 3D Detector with Diverse 2D Annotations","created":"2024-12-16","cited_by_count":4}],"next_cursor":null}