{"list":"other","total":68,"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":"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":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"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":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1801.07829","title":"Dynamic Graph CNN for Learning on Point Clouds","created":"2018-01-24","cited_by_count":2223},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"1904.08755","title":"4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks","created":"2019-04-18","cited_by_count":1208},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2111.14819","title":"Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling","created":"2021-11-29","cited_by_count":653},{"id":"2010.04592","title":"Contrastive Learning with Hard Negative Samples","created":"2020-10-09","cited_by_count":628},{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543},{"id":"1908.04616","title":"Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data","created":"2019-08-13","cited_by_count":532},{"id":"2112.01455","title":"Zero-Shot Text-Guided Object Generation with Dream Fields","created":"2021-12-02","cited_by_count":513},{"id":"2007.10985","title":"PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding","created":"2020-07-21","cited_by_count":504},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"2203.06604","title":"Masked Autoencoders for Point Cloud Self-supervised Learning","created":"2022-03-13","cited_by_count":459},{"id":"2206.04670","title":"PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies","created":"2022-06-09","cited_by_count":436},{"id":"2010.01028","title":"Hard Negative Mixing for Contrastive Learning","created":"2020-10-02","cited_by_count":402},{"id":"2202.07123","title":"Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework","created":"2022-02-15","cited_by_count":379},{"id":"2110.06199","title":"ABO: Dataset and Benchmarks for Real-World 3D Object Understanding","created":"2021-10-12","cited_by_count":366},{"id":"2112.03221","title":"Text2Mesh: Text-Driven Neural Stylization for Meshes","created":"2021-12-06","cited_by_count":334},{"id":"2009.09633","title":"3D-FUTURE: 3D Furniture shape with TextURE","created":"2020-09-21","cited_by_count":311},{"id":"2302.07241","title":"ConceptFusion: Open-set Multimodal 3D Mapping","created":"2023-02-14","cited_by_count":304},{"id":"2206.05836","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","created":"2022-06-12","cited_by_count":275},{"id":"2110.02624","title":"CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation","created":"2021-10-06","cited_by_count":254},{"id":"2204.07761","title":"Language-Grounded Indoor 3D Semantic Segmentation in the Wild","created":"2022-04-16","cited_by_count":246},{"id":"2101.02691","title":"Self-Supervised Pretraining of 3D Features on any Point-Cloud","created":"2021-01-07","cited_by_count":217},{"id":"2010.01089","title":"Unsupervised Point Cloud Pre-Training via Occlusion Completion","created":"2020-10-02","cited_by_count":186},{"id":"2301.04926","title":"CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP","created":"2023-01-12","cited_by_count":181},{"id":"2211.16312","title":"PLA: Language-Driven Open-Vocabulary 3D Scene Understanding","created":"2022-11-29","cited_by_count":177},{"id":"2302.02318","title":"Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining","created":"2023-02-05","cited_by_count":164},{"id":"2210.01055","title":"CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training","created":"2022-10-03","cited_by_count":160},{"id":"2212.14704","title":"Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models","created":"2022-12-28","cited_by_count":151},{"id":"1808.10322","title":"PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors","created":"2018-08-30","cited_by_count":141},{"id":"2212.01558","title":"PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models","created":"2022-12-03","cited_by_count":118},{"id":"2003.12641","title":"Self-Supervised Learning for Domain Adaptation on Point-Clouds","created":"2020-03-29","cited_by_count":99},{"id":"2207.11514","title":"Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models","created":"2022-07-23","cited_by_count":95},{"id":"2304.00962","title":"RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding","created":"2023-04-03","cited_by_count":94},{"id":"2303.04748","title":"CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP","created":"2023-03-08","cited_by_count":89},{"id":"2304.00788","title":"Open-Vocabulary Point-Cloud Object Detection without 3D Annotation","created":"2023-04-03","cited_by_count":81},{"id":"2303.11313","title":"CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition","created":"2023-03-20","cited_by_count":77},{"id":"2003.12971","title":"Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds","created":"2020-03-29","cited_by_count":75},{"id":"2008.00305","title":"Self-supervised Learning of Point Clouds via Orientation Estimation","created":"2020-08-01","cited_by_count":72},{"id":"2303.12417","title":"CLIP$^2$: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data","created":"2023-03-22","cited_by_count":69},{"id":"2006.02598","title":"Info3D: Representation Learning on 3D Objects using Mutual Information Maximization and Contrastive Learning","created":"2020-06-04","cited_by_count":68},{"id":"2009.14168","title":"Self-Supervised Few-Shot Learning on Point Clouds","created":"2020-09-29","cited_by_count":66},{"id":"2304.04909","title":"SATR: Zero-Shot Semantic Segmentation of 3D Shapes","created":"2023-04-11","cited_by_count":62},{"id":"2212.01406","title":"ClipFace: Text-guided Editing of Textured 3D Morphable Models","created":"2022-12-02","cited_by_count":60},{"id":"2209.15172","title":"Understanding Pure CLIP Guidance for Voxel Grid NeRF Models","created":"2022-09-30","cited_by_count":56},{"id":"2110.04076","title":"Self-supervised Point Cloud Prediction Using 3D Spatio-temporal Convolutional Networks","created":"2021-09-28","cited_by_count":42},{"id":"2109.12922","title":"ClipMatrix: Text-controlled Creation of 3D Textured Meshes","created":"2021-09-27","cited_by_count":40},{"id":"2207.00531","title":"Masked Autoencoder for Self-Supervised Pre-training on Lidar Point Clouds","created":"2022-07-01","cited_by_count":39},{"id":"2202.06079","title":"Text and Image Guided 3D Avatar Generation and Manipulation","created":"2022-02-12","cited_by_count":35},{"id":"2212.06858","title":"LidarCLIP or: How I Learned to Talk to Point Clouds","created":"2022-12-13","cited_by_count":33},{"id":"2209.04145","title":"ISS: Image as Stepping Stone for Text-Guided 3D Shape Generation","created":"2022-09-09","cited_by_count":27},{"id":"2301.07584","title":"Joint Representation Learning for Text and 3D Point Cloud","created":"2023-01-18","cited_by_count":14},{"id":"2103.06134","title":"Sim2Real 3D Object Classification using Spherical Kernel Point Convolution and a Deep Center Voting Scheme","created":"2021-03-10","cited_by_count":1}],"next_cursor":null}