{"list":"other","total":78,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"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":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"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":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"1708.02002","title":"Focal Loss for Dense Object Detection","created":"2017-08-07","cited_by_count":752},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2012.07177","title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation","created":"2020-12-13","cited_by_count":596},{"id":"1504.06375","title":"Holistically-Nested Edge Detection","created":"2015-04-24","cited_by_count":592},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"1910.09700","title":"Quantifying the Carbon Emissions of Machine Learning","created":"2019-10-21","cited_by_count":521},{"id":"1707.09457","title":"Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints","created":"2017-07-29","cited_by_count":420},{"id":"2211.06220","title":"OneFormer: One Transformer to Rule Universal Image Segmentation","created":"2022-11-10","cited_by_count":328},{"id":"2106.14855","title":"K-Net: Towards Unified Image Segmentation","created":"2021-06-28","cited_by_count":212},{"id":"2102.06583","title":"Reviving Iterative Training with Mask Guidance for Interactive Segmentation","created":"2021-02-12","cited_by_count":163},{"id":"1603.04042","title":"Deep Interactive Object Selection","created":"2016-03-13","cited_by_count":160},{"id":"1912.07726","title":"Towards Fairer Datasets: Filtering and Balancing the Distribution of the People Subtree in the ImageNet Hierarchy","created":"2019-12-16","cited_by_count":156},{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154},{"id":"1906.02659","title":"Does Object Recognition Work for Everyone?","created":"2019-06-06","cited_by_count":151},{"id":"1905.01489","title":"WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving","created":"2019-05-04","cited_by_count":144},{"id":"2209.13064","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","created":"2022-09-26","cited_by_count":140},{"id":"1711.09081","title":"Deep Extreme Cut: From Extreme Points to Object Segmentation","created":"2017-11-24","cited_by_count":127},{"id":"2210.11006","title":"SimpleClick: Interactive Image Segmentation with Simple Vision Transformers","created":"2022-10-20","cited_by_count":111},{"id":"2108.06753","title":"Learning Open-World Object Proposals without Learning to Classify","created":"2021-08-15","cited_by_count":109},{"id":"2204.02574","title":"FocalClick: Towards Practical Interactive Image Segmentation","created":"2022-04-06","cited_by_count":102},{"id":"1705.00108","title":"Semi-supervised sequence tagging with bidirectional language models","created":"2017-04-29","cited_by_count":86},{"id":"1708.02750","title":"Extreme clicking for efficient object annotation","created":"2017-08-09","cited_by_count":81},{"id":"2208.03826","title":"Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications","created":"2022-08-07","cited_by_count":78},{"id":"2301.08247","title":"Multiview Compressive Coding for 3D Reconstruction","created":"2023-01-19","cited_by_count":71},{"id":"1406.5549","title":"Fast Edge Detection Using Structured Forests","created":"2014-06-20","cited_by_count":65},{"id":"2206.08931","title":"CrowdWorkSheets: Accounting for Individual and Collective Identities Underlying Crowdsourced Dataset Annotation","created":"2022-06-09","cited_by_count":59},{"id":"1805.04398","title":"Iteratively Trained Interactive Segmentation","created":"2018-05-11","cited_by_count":52},{"id":"2106.02740","title":"ZeroWaste Dataset: Towards Deformable Object Segmentation in Cluttered Scenes","created":"2021-06-04","cited_by_count":47},{"id":"2105.02317","title":"A Step Toward More Inclusive People Annotations for Fairness","created":"2021-05-05","cited_by_count":46},{"id":"2007.08097","title":"TrashCan: A Semantically-Segmented Dataset towards Visual Detection of Marine Debris","created":"2020-07-16","cited_by_count":45},{"id":"2204.06107","title":"Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity","created":"2022-04-12","cited_by_count":41},{"id":"2203.08566","title":"EDTER: Edge Detection with Transformer","created":"2022-03-16","cited_by_count":36},{"id":"2108.07020","title":"Towards Real-World Prohibited Item Detection: A Large-Scale X-ray Benchmark","created":"2021-08-16","cited_by_count":31},{"id":"2005.13359","title":"NDD20: A large-scale few-shot dolphin dataset for coarse and fine-grained categorisation","created":"2020-05-27","cited_by_count":24},{"id":"2203.03238","title":"Semantic Segmentation in Art Paintings","created":"2022-03-07","cited_by_count":23},{"id":"2003.07932","title":"Getting to 99% Accuracy in Interactive Segmentation","created":"2020-03-17","cited_by_count":19},{"id":"2203.01902","title":"Instance Segmentation for Autonomous Log Grasping in Forestry Operations","created":"2022-03-03","cited_by_count":16},{"id":"1807.08555","title":"Iterative Interaction Training for Segmentation Editing Networks","created":"2018-07-23","cited_by_count":14},{"id":"2109.15068","title":"iShape: A First Step Towards Irregular Shape Instance Segmentation","created":"2021-09-30","cited_by_count":12},{"id":"2112.09902","title":"3D Instance Segmentation of MVS Buildings","created":"2021-12-18","cited_by_count":12},{"id":"2209.09070","title":"SOCRATES: A Stereo Camera Trap for Monitoring of Biodiversity","created":"2022-09-19","cited_by_count":10},{"id":"1505.05836","title":"Object-Proposal Evaluation Protocol is 'Gameable'","created":"2015-05-21","cited_by_count":9}],"next_cursor":null}