{"list":"other","total":65,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2006.10739","title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","created":"2020-06-18","cited_by_count":2200},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"id":"2103.01458","title":"Diffusion Probabilistic Models for 3D Point Cloud Generation","created":"2021-03-02","cited_by_count":735},{"id":"2303.13873","title":"Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation","created":"2023-03-24","cited_by_count":687},{"id":"2308.06571","title":"ModelScope Text-to-Video Technical Report","created":"2023-08-12","cited_by_count":658},{"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":"1906.12320","title":"PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows","created":"2019-06-28","cited_by_count":488},{"id":"2210.14896","title":"DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models","created":"2022-10-26","cited_by_count":379},{"id":"2309.16585","title":"Text-to-3D using Gaussian Splatting","created":"2023-09-28","cited_by_count":299},{"id":"2311.12320","title":"A Survey on Multimodal Large Language Models for Autonomous Driving","created":"2023-11-21","cited_by_count":290},{"id":"2204.08583","title":"VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance","created":"2022-04-18","cited_by_count":285},{"id":"2202.04053","title":"DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models","created":"2022-02-08","cited_by_count":230},{"id":"2111.01007","title":"Projected GANs Converge Faster","created":"2021-11-01","cited_by_count":208},{"id":"1704.05519","title":"Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art","created":"2017-04-18","cited_by_count":182},{"id":"1803.08495","title":"Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings","created":"2018-03-22","cited_by_count":169},{"id":"2308.12964","title":"Dense Text-to-Image Generation with Attention Modulation","created":"2023-08-24","cited_by_count":163},{"id":"2310.08710","title":"Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research","created":"2023-10-12","cited_by_count":160},{"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":"2006.09348","title":"LiDARsim: Realistic LiDAR Simulation by Leveraging the Real World","created":"2020-06-16","cited_by_count":137},{"id":"1903.08701","title":"LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving","created":"2019-03-20","cited_by_count":133},{"id":"2303.17597","title":"Robo3D: Towards Robust and Reliable 3D Perception against Corruptions","created":"2023-03-30","cited_by_count":129},{"id":"2111.13792","title":"LAFITE: Towards Language-Free Training for Text-to-Image Generation","created":"2021-11-27","cited_by_count":128},{"id":"2211.17106","title":"Diffusion Probabilistic Model Made Slim","created":"2022-11-27","cited_by_count":121},{"id":"2211.16231","title":"Curriculum Temperature for Knowledge Distillation","created":"2022-11-29","cited_by_count":112},{"id":"2304.06720","title":"Expressive Text-to-Image Generation with Rich Text","created":"2023-04-13","cited_by_count":89},{"id":"2007.10170","title":"Discrete Point Flow Networks for Efficient Point Cloud Generation","created":"2020-07-20","cited_by_count":87},{"id":"2107.13802","title":"RigNet: Repetitive Image Guided Network for Depth Completion","created":"2021-07-29","cited_by_count":80},{"id":"1812.01180","title":"Deep Generative Modeling of LiDAR Data","created":"2018-12-04","cited_by_count":71},{"id":"2203.14622","title":"Towards Implicit Text-Guided 3D Shape Generation","created":"2022-03-28","cited_by_count":68},{"id":"2106.12735","title":"Multi-Modal 3D Object Detection in Autonomous Driving: a Survey","created":"2021-06-24","cited_by_count":63},{"id":"2203.00386","title":"CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP","created":"2022-03-01","cited_by_count":60},{"id":"2212.01747","title":"Fast Point Cloud Generation with Straight Flows","created":"2022-12-04","cited_by_count":56},{"id":"2007.05361","title":"Progressive Point Cloud Deconvolution Generation Network","created":"2020-07-10","cited_by_count":46},{"id":"2403.15008","title":"Tri-Perspective View Decomposition for Geometry-Aware Depth Completion","created":"2024-03-22","cited_by_count":42},{"id":"2106.13381","title":"To the Point: Efficient 3D Object Detection in the Range Image with Graph Convolution Kernels","created":"2021-06-25","cited_by_count":39},{"id":"2104.08911","title":"DW-GAN: A Discrete Wavelet Transform GAN for NonHomogeneous Dehazing","created":"2021-04-18","cited_by_count":38},{"id":"2202.09367","title":"Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer","created":"2022-02-18","cited_by_count":38},{"id":"2306.10533","title":"Point-Cloud Completion with Pretrained Text-to-image Diffusion Models","created":"2023-06-18","cited_by_count":37},{"id":"2308.02874","title":"Sketch and Text Guided Diffusion Model for Colored Point Cloud Generation","created":"2023-08-05","cited_by_count":36},{"id":"2303.05916","title":"GECCO: Geometrically-Conditioned Point Diffusion Models","created":"2023-03-10","cited_by_count":24},{"id":"2304.06312","title":"Survey on LiDAR Perception in Adverse Weather Conditions","created":"2023-04-13","cited_by_count":24},{"id":"2203.09855","title":"Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completion","created":"2022-03-18","cited_by_count":23},{"id":"2401.03788","title":"Low-light Image Enhancement via CLIP-Fourier Guided Wavelet Diffusion","created":"2024-01-08","cited_by_count":19},{"id":"2305.16129","title":"Energy-based Detection of Adverse Weather Effects in LiDAR Data","created":"2023-05-25","cited_by_count":7},{"id":"2205.00816","title":"Semantic localization on BIM-generated maps using a 3D LiDAR sensor","created":"2022-05-02","cited_by_count":6},{"id":"2303.09270","title":"SpectralCLIP: Preventing Artifacts in Text-Guided Style Transfer from a Spectral Perspective","created":"2023-03-16","cited_by_count":3}],"next_cursor":null}