{"list":"other","total":51,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"id":"2201.02605","title":"Detecting Twenty-thousand Classes using Image-level Supervision","created":"2022-01-07","cited_by_count":614},{"id":"2004.09813","title":"Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation","created":"2020-04-21","cited_by_count":593},{"id":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"id":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"id":"2311.12871","title":"An Embodied Generalist Agent in 3D World","created":"2023-11-18","cited_by_count":365},{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346},{"id":"2004.01658","title":"PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation","created":"2020-04-03","cited_by_count":321},{"id":"2210.07474","title":"SQA3D: Situated Question Answering in 3D Scenes","created":"2022-10-14","cited_by_count":314},{"id":"2306.13631","title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","created":"2023-06-23","cited_by_count":289},{"id":"2204.07761","title":"Language-Grounded Indoor 3D Semantic Segmentation in the Wild","created":"2022-04-16","cited_by_count":246},{"id":"2012.02206","title":"Scan2Cap: Context-aware Dense Captioning in RGB-D Scans","created":"2020-12-03","cited_by_count":218},{"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":"2308.04352","title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","created":"2023-08-08","cited_by_count":204},{"id":"2203.01509","title":"SoftGroup for 3D Instance Segmentation on Point Clouds","created":"2022-03-03","cited_by_count":200},{"id":"2312.10032","title":"Osprey: Pixel Understanding with Visual Instruction Tuning","created":"2023-12-15","cited_by_count":159},{"id":"2108.02350","title":"Hierarchical Aggregation for 3D Instance Segmentation","created":"2021-08-05","cited_by_count":127},{"id":"2312.10671","title":"Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance","created":"2023-12-17","cited_by_count":124},{"id":"2209.14941","title":"EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding","created":"2022-09-29","cited_by_count":99},{"id":"2312.11557","title":"SAI3D: Segment Any Instance in 3D Scenes","created":"2023-12-17","cited_by_count":90},{"id":"2311.02873","title":"OVIR-3D: Open-Vocabulary 3D Instance Retrieval Without Training on 3D Data","created":"2023-11-06","cited_by_count":81},{"id":"2301.02508","title":"End-to-End 3D Dense Captioning with Vote2Cap-DETR","created":"2023-01-06","cited_by_count":78},{"id":"2011.13328","title":"DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution","created":"2020-11-26","cited_by_count":75},{"id":"2310.15200","title":"Open-Set Image Tagging with Multi-Grained Text Supervision","created":"2023-10-23","cited_by_count":67},{"id":"2312.17232","title":"Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels","created":"2023-12-28","cited_by_count":64},{"id":"2306.08045","title":"Efficient 3D Semantic Segmentation with Superpoint Transformer","created":"2023-06-13","cited_by_count":57},{"id":"2401.07745","title":"MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation","created":"2024-01-15","cited_by_count":56},{"id":"2304.06061","title":"CLIP-Guided Vision-Language Pre-training for Question Answering in 3D Scenes","created":"2023-04-12","cited_by_count":55},{"id":"2303.00246","title":"ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution","created":"2023-03-01","cited_by_count":53},{"id":"2310.17504","title":"Three Pillars improving Vision Foundation Model Distillation for Lidar","created":"2023-10-26","cited_by_count":44},{"id":"2204.10688","title":"Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds","created":"2022-04-22","cited_by_count":40},{"id":"2308.00353","title":"Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding","created":"2023-08-01","cited_by_count":38},{"id":"2312.08372","title":"SAM-guided Graph Cut for 3D Instance Segmentation","created":"2023-12-13","cited_by_count":35},{"id":"2403.10191","title":"Generative Region-Language Pretraining for Open-Ended Object Detection","created":"2024-03-15","cited_by_count":29},{"id":"2005.08144","title":"High-dimensional Convolutional Networks for Geometric Pattern Recognition","created":"2020-05-17","cited_by_count":24},{"id":"2306.02329","title":"Multi-CLIP: Contrastive Vision-Language Pre-training for Question Answering tasks in 3D Scenes","created":"2023-06-04","cited_by_count":22},{"id":"2303.13396","title":"Zero-guidance Segmentation Using Zero Segment Labels","created":"2023-03-23","cited_by_count":18},{"id":"2401.06704","title":"Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering","created":"2024-01-12","cited_by_count":14},{"id":"2312.02142","title":"Object Recognition as Next Token Prediction","created":"2023-12-04","cited_by_count":12},{"id":"2311.08400","title":"Towards Open-Ended Visual Recognition with Large Language Model","created":"2023-11-14","cited_by_count":8}],"next_cursor":null}