{"list":"other","total":64,"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"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":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"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":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"1801.09847","title":"Open3D: A Modern Library for 3D Data Processing","created":"2018-01-30","cited_by_count":721},{"id":"2201.02605","title":"Detecting Twenty-thousand Classes using Image-level Supervision","created":"2022-01-07","cited_by_count":614},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"1505.00880","title":"Multi-view Convolutional Neural Networks for 3D Shape Recognition","created":"2015-05-05","cited_by_count":565},{"id":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559},{"id":"2305.03726","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","created":"2023-05-05","cited_by_count":550},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532},{"id":"1812.02713","title":"PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding","created":"2018-12-06","cited_by_count":526},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501},{"id":"2112.12143","title":"Scaling Open-Vocabulary Image Segmentation with Image-Level Labels","created":"2021-12-22","cited_by_count":473},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"2210.05666","title":"Point Transformer V2: Grouped Vector Attention and Partition-based Pooling","created":"2022-10-11","cited_by_count":388},{"id":"2303.04803","title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models","created":"2023-03-08","cited_by_count":375},{"id":"2109.08141","title":"An End-to-End Transformer Model for 3D Object Detection","created":"2021-09-16","cited_by_count":329},{"id":"2210.03105","title":"Mask3D: Mask Transformer for 3D Semantic Instance Segmentation","created":"2022-10-06","cited_by_count":303},{"id":"2307.03601","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","created":"2023-07-07","cited_by_count":302},{"id":"2306.13631","title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","created":"2023-06-23","cited_by_count":289},{"id":"1903.00241","title":"Mask Scoring R-CNN","created":"2019-03-01","cited_by_count":266},{"id":"2204.07761","title":"Language-Grounded Indoor 3D Semantic Segmentation in the Wild","created":"2022-04-16","cited_by_count":246},{"id":"2203.01509","title":"SoftGroup for 3D Instance Segmentation on Point Clouds","created":"2022-03-03","cited_by_count":200},{"id":"2211.11682","title":"PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning","created":"2022-11-21","cited_by_count":187},{"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":"2210.01055","title":"CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training","created":"2022-10-03","cited_by_count":160},{"id":"1704.03847","title":"Semantic3D.net: A new Large-scale Point Cloud Classification Benchmark","created":"2017-04-12","cited_by_count":158},{"id":"2306.03908","title":"SAM3D: Segment Anything in 3D Scenes","created":"2023-06-06","cited_by_count":157},{"id":"2208.08984","title":"Open-Vocabulary Universal Image Segmentation with MaskCLIP","created":"2022-08-18","cited_by_count":132},{"id":"2112.13762","title":"MSeg: A Composite Dataset for Multi-domain Semantic Segmentation","created":"2021-12-27","cited_by_count":122},{"id":"2305.14167","title":"DetGPT: Detect What You Need via Reasoning","created":"2023-05-23","cited_by_count":112},{"id":"2007.13138","title":"Virtual Multi-view Fusion for 3D Semantic Segmentation","created":"2020-07-26","cited_by_count":99},{"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":"2304.00788","title":"Open-Vocabulary Point-Cloud Object Detection without 3D Annotation","created":"2023-04-03","cited_by_count":81},{"id":"2009.03137","title":"Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges","created":"2020-09-07","cited_by_count":80},{"id":"2003.08284","title":"Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways","created":"2020-03-18","cited_by_count":77},{"id":"2004.11985","title":"DALES: A Large-scale Aerial LiDAR Data Set for Semantic Segmentation","created":"2020-04-14","cited_by_count":66},{"id":"1712.00032","title":"Paris-Lille-3D: a large and high-quality ground truth urban point cloud dataset for automatic segmentation and classification","created":"2017-11-30","cited_by_count":65},{"id":"2108.06230","title":"Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Clouds","created":"2021-08-13","cited_by_count":55},{"id":"2203.09065","title":"STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset","created":"2022-03-17","cited_by_count":53},{"id":"2211.11720","title":"Multitask Vision-Language Prompt Tuning","created":"2022-11-21","cited_by_count":51},{"id":"2201.04494","title":"SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Clouds","created":"2022-01-12","cited_by_count":50},{"id":"2106.04180","title":"Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models","created":"2021-06-08","cited_by_count":41},{"id":"2211.14241","title":"Look Around and Refer: 2D Synthetic Semantics Knowledge Distillation for 3D Visual Grounding","created":"2022-11-25","cited_by_count":41},{"id":"2303.11324","title":"Open-vocabulary Panoptic Segmentation with Embedding Modulation","created":"2023-03-20","cited_by_count":39},{"id":"2308.00353","title":"Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding","created":"2023-08-01","cited_by_count":38},{"id":"2303.14541","title":"UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenes","created":"2023-03-25","cited_by_count":31},{"id":"2008.04968","title":"Campus3D: A Photogrammetry Point Cloud Benchmark for Hierarchical Understanding of Outdoor Scene","created":"2020-08-11","cited_by_count":27},{"id":"1907.04758","title":"SynthCity: A large scale synthetic point cloud","created":"2019-07-10","cited_by_count":26},{"id":"2203.09155","title":"AdaSplats: Adaptive Splatting of Point Clouds for Accurate 3D Modeling and Real-time High-Fidelity LiDAR Simulation","created":"2022-03-17","cited_by_count":2}],"next_cursor":null}