{"list":"other","total":53,"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":"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":"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"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":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"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":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"2011.09157","title":"Dense Contrastive Learning for Self-Supervised Visual Pre-Training","created":"2020-11-18","cited_by_count":512},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"2112.12143","title":"Scaling Open-Vocabulary Image Segmentation with Image-Level Labels","created":"2021-12-22","cited_by_count":473},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"1912.04488","title":"SOLO: Segmenting Objects by Locations","created":"2019-12-10","cited_by_count":289},{"id":"2112.14757","title":"A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model","created":"2021-12-29","cited_by_count":223},{"id":"2303.11797","title":"CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation","created":"2023-03-21","cited_by_count":219},{"id":"2106.14855","title":"K-Net: Towards Unified Image Segmentation","created":"2021-06-28","cited_by_count":212},{"id":"1909.13032","title":"Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning","created":"2019-09-28","cited_by_count":182},{"id":"2104.12099","title":"Visual Saliency Transformer","created":"2021-04-25","cited_by_count":175},{"id":"2105.01928","title":"Instances as Queries","created":"2021-05-05","cited_by_count":158},{"id":"2101.07663","title":"Salient Object Detection via Integrity Learning","created":"2021-01-19","cited_by_count":133},{"id":"2202.12181","title":"FreeSOLO: Learning to Segment Objects without Annotations","created":"2022-02-24","cited_by_count":102},{"id":"1903.12174","title":"TensorMask: A Foundation for Dense Object Segmentation","created":"2019-03-28","cited_by_count":101},{"id":"2104.07918","title":"Weakly Supervised Object Localization and Detection: A Survey","created":"2021-04-16","cited_by_count":84},{"id":"1712.02170","title":"Detecting Curve Text in the Wild: New Dataset and New Solution","created":"2017-12-06","cited_by_count":83},{"id":"2106.04550","title":"DETReg: Unsupervised Pretraining with Region Priors for Object Detection","created":"2021-06-08","cited_by_count":76},{"id":"2206.08657","title":"BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learning","created":"2022-06-17","cited_by_count":56},{"id":"2105.00637","title":"ISTR: End-to-End Instance Segmentation with Transformers","created":"2021-05-03","cited_by_count":52},{"id":"2003.13954","title":"FGN: Fully Guided Network for Few-Shot Instance Segmentation","created":"2020-03-31","cited_by_count":46},{"id":"1811.11507","title":"One-Shot Instance Segmentation","created":"2018-11-28","cited_by_count":43},{"id":"2303.11324","title":"Open-vocabulary Panoptic Segmentation with Embedding Modulation","created":"2023-03-20","cited_by_count":39},{"id":"1603.08678","title":"Instance-sensitive Fully Convolutional Networks","created":"2016-03-29","cited_by_count":36},{"id":"1812.06314","title":"PiCANet: Pixel-wise Contextual Attention Learning for Accurate Saliency Detection","created":"2018-12-15","cited_by_count":28},{"id":"2102.09133","title":"Densely Nested Top-Down Flows for Salient Object Detection","created":"2021-02-18","cited_by_count":23},{"id":"2203.13427","title":"Noisy Boundaries: Lemon or Lemonade for Semi-supervised Instance Segmentation?","created":"2022-03-25","cited_by_count":21},{"id":"2307.11077","title":"AlignDet: Aligning Pre-training and Fine-tuning in Object Detection","created":"2023-07-20","cited_by_count":14},{"id":"2302.01171","title":"Boosting Low-Data Instance Segmentation by Unsupervised Pre-training with Saliency Prompt","created":"2023-02-02","cited_by_count":11},{"id":"2312.01169","title":"Virtual Category Learning: A Semi-Supervised Learning Method for Dense Prediction with Extremely Limited Labels","created":"2023-12-02","cited_by_count":10}],"next_cursor":null}