{"list":"other","total":52,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"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":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"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":"1904.09664","title":"Deep Hough Voting for 3D Object Detection in Point Clouds","created":"2019-04-21","cited_by_count":648},{"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":"2203.06604","title":"Masked Autoencoders for Point Cloud Self-supervised Learning","created":"2022-03-13","cited_by_count":459},{"id":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346},{"id":"2109.08141","title":"An End-to-End Transformer Model for 3D Object Detection","created":"2021-09-16","cited_by_count":329},{"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":"2104.08541","title":"TransVG: End-to-End Visual Grounding with Transformers","created":"2021-04-17","cited_by_count":271},{"id":"2212.05171","title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","created":"2022-12-10","cited_by_count":267},{"id":"2205.14401","title":"Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training","created":"2022-05-28","cited_by_count":264},{"id":"2012.02206","title":"Scan2Cap: Context-aware Dense Captioning in RGB-D Scans","created":"2020-12-03","cited_by_count":218},{"id":"2010.01089","title":"Unsupervised Point Cloud Pre-Training via Occlusion Completion","created":"2020-10-02","cited_by_count":186},{"id":"2305.10764","title":"OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding","created":"2023-05-18","cited_by_count":184},{"id":"2111.13196","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","created":"2021-11-25","cited_by_count":162},{"id":"2212.06785","title":"Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders","created":"2022-12-13","cited_by_count":144},{"id":"2105.11450","title":"SAT: 2D Semantics Assisted Training for 3D Visual Grounding","created":"2021-05-24","cited_by_count":124},{"id":"2212.08320","title":"Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?","created":"2022-12-16","cited_by_count":122},{"id":"2307.08581","title":"BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs","created":"2023-07-17","cited_by_count":114},{"id":"2203.00843","title":"X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning","created":"2022-03-02","cited_by_count":70},{"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":"2203.05203","title":"MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes","created":"2022-03-10","cited_by_count":46},{"id":"2307.13363","title":"3DRP-Net: 3D Relative Position-aware Network for 3D Visual Grounding","created":"2023-07-25","cited_by_count":25},{"id":"2307.09267","title":"Distilling Coarse-to-Fine Semantic Matching Knowledge for Weakly Supervised 3D Visual Grounding","created":"2023-07-18","cited_by_count":18}],"next_cursor":null}