{"list":"other","total":218,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"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":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"2103.13415","title":"Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields","created":"2021-03-24","cited_by_count":1964},{"id":"1812.05784","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","created":"2018-12-14","cited_by_count":1715},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2012.02190","title":"pixelNeRF: Neural Radiance Fields from One or Few Images","created":"2020-12-03","cited_by_count":1584},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"1711.06396","title":"VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection","created":"2017-11-17","cited_by_count":1323},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"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":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"2008.02268","title":"NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections","created":"2020-08-05","cited_by_count":1232},{"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":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2008.05711","title":"Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D","created":"2020-08-13","cited_by_count":1044},{"id":"2103.10360","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","created":"2021-03-18","cited_by_count":1031},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"1812.04244","title":"PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud","created":"2018-12-11","cited_by_count":941},{"id":"1912.13192","title":"PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection","created":"2019-12-31","cited_by_count":891},{"id":"2010.07492","title":"NeRF++: Analyzing and Improving Neural Radiance Fields","created":"2020-10-15","cited_by_count":861},{"id":"2205.13542","title":"BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation","created":"2022-05-26","cited_by_count":850},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843},{"id":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738},{"id":"1911.02620","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","created":"2019-11-06","cited_by_count":732},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"2112.11790","title":"BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View","created":"2021-12-22","cited_by_count":713},{"id":"2301.00493","title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","created":"2023-01-02","cited_by_count":707},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651},{"id":"2309.17080","title":"GAIA-1: A Generative World Model for Autonomous Driving","created":"2023-09-29","cited_by_count":637},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"1911.11236","title":"RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds","created":"2019-11-25","cited_by_count":585},{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575},{"id":"2206.10092","title":"BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection","created":"2022-06-21","cited_by_count":572},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"2203.05625","title":"PETR: Position Embedding Transformation for Multi-View 3D Object Detection","created":"2022-03-10","cited_by_count":552},{"id":"2312.14150","title":"DriveLM: Driving with Graph Visual Question Answering","created":"2023-12-21","cited_by_count":536},{"id":"2007.10985","title":"PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding","created":"2020-07-21","cited_by_count":504},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"2310.01412","title":"DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model","created":"2023-10-02","cited_by_count":461},{"id":"2203.06604","title":"Masked Autoencoders for Point Cloud Self-supervised Learning","created":"2022-03-13","cited_by_count":459},{"id":"2104.10956","title":"FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection","created":"2021-04-22","cited_by_count":447},{"id":"2007.16100","title":"Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution","created":"2020-07-31","cited_by_count":423},{"id":"2012.15712","title":"Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection","created":"2020-12-31","cited_by_count":410},{"id":"2206.14176","title":"DayDreamer: World Models for Physical Robot Learning","created":"2022-06-28","cited_by_count":400},{"id":"1808.06601","title":"Video-to-Video Synthesis","created":"2018-08-20","cited_by_count":390},{"id":"2303.04803","title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models","created":"2023-03-08","cited_by_count":375},{"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":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"id":"2310.01415","title":"GPT-Driver: Learning to Drive with GPT","created":"2023-10-02","cited_by_count":347},{"id":"1605.06457","title":"Virtual Worlds as Proxy for Multi-Object Tracking Analysis","created":"2016-05-20","cited_by_count":341},{"id":"2304.14365","title":"Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving","created":"2023-04-27","cited_by_count":332},{"id":"2311.17918","title":"Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving","created":"2023-11-29","cited_by_count":319},{"id":"2303.09551","title":"SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving","created":"2023-03-16","cited_by_count":316},{"id":"2205.09853","title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","created":"2022-05-19","cited_by_count":309},{"id":"2308.01898","title":"UniSim: A Neural Closed-Loop Sensor Simulator","created":"2023-08-03","cited_by_count":297},{"id":"2205.11495","title":"Flexible Diffusion Modeling of Long Videos","created":"2022-05-23","cited_by_count":294},{"id":"2304.05316","title":"OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction","created":"2023-04-11","cited_by_count":293},{"id":"2309.09777","title":"DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving","created":"2023-09-18","cited_by_count":261},{"id":"2310.02601","title":"MagicDrive: Street View Generation with Diverse 3D Geometry Control","created":"2023-10-04","cited_by_count":252},{"id":"2109.02497","title":"Voxel Transformer for 3D Object Detection","created":"2021-09-06","cited_by_count":247},{"id":"2003.00492","title":"PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling","created":"2020-03-01","cited_by_count":239},{"id":"2304.11968","title":"Track Anything: Segment Anything Meets Videos","created":"2023-04-24","cited_by_count":234},{"id":"2304.06790","title":"Inpaint Anything: Segment Anything Meets Image Inpainting","created":"2023-04-13","cited_by_count":233},{"id":"2311.16038","title":"OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving","created":"2023-11-27","cited_by_count":233},{"id":"1809.08495","title":"SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud","created":"2018-09-22","cited_by_count":228},{"id":"1807.11546","title":"Textual Explanations for Self-Driving Vehicles","created":"2018-07-30","cited_by_count":226},{"id":"2106.11097","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","created":"2021-06-21","cited_by_count":225},{"id":"2303.03991","title":"OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception","created":"2023-03-07","cited_by_count":221},{"id":"2401.01339","title":"Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting","created":"2024-01-02","cited_by_count":221},{"id":"2106.11037","title":"One Million Scenes for Autonomous Driving: ONCE Dataset","created":"2021-06-21","cited_by_count":218},{"id":"2101.02691","title":"Self-Supervised Pretraining of 3D Features on any Point-Cloud","created":"2021-01-07","cited_by_count":217}],"next_cursor":"100"}