{"list":"other","total":58,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"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":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"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":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"1904.08189","title":"CenterNet: Keypoint Triplets for Object Detection","created":"2019-04-17","cited_by_count":654},{"id":"1901.07518","title":"Hybrid Task Cascade for Instance Segmentation","created":"2019-01-22","cited_by_count":481},{"id":"1911.08287","title":"Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression","created":"2019-11-19","cited_by_count":459},{"id":"1904.02689","title":"YOLACT: Real-time Instance Segmentation","created":"2019-04-04","cited_by_count":443},{"id":"1912.08193","title":"PointRend: Image Segmentation as Rendering","created":"2019-12-17","cited_by_count":440},{"id":"1906.09756","title":"Cascade R-CNN: High Quality Object Detection and Instance Segmentation","created":"2019-06-24","cited_by_count":429},{"id":"1803.10464","title":"Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation","created":"2018-03-28","cited_by_count":321},{"id":"2003.05664","title":"Conditional Convolutions for Instance Segmentation","created":"2020-03-12","cited_by_count":314},{"id":"1506.02106","title":"What's the Point: Semantic Segmentation with Point Supervision","created":"2015-06-06","cited_by_count":298},{"id":"1503.01640","title":"BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation","created":"2015-03-05","cited_by_count":238},{"id":"2106.14855","title":"K-Net: Towards Unified Image Segmentation","created":"2021-06-28","cited_by_count":212},{"id":"1909.13226","title":"PolarMask: Single Shot Instance Segmentation with Polar Representation","created":"2019-09-29","cited_by_count":188},{"id":"2105.01928","title":"Instances as Queries","created":"2021-05-05","cited_by_count":158},{"id":"2206.07669","title":"A Unified Sequence Interface for Vision Tasks","created":"2022-06-15","cited_by_count":152},{"id":"2012.02310","title":"BoxInst: High-Performance Instance Segmentation with Box Annotations","created":"2020-12-03","cited_by_count":151},{"id":"1803.09569","title":"On Regularized Losses for Weakly-supervised CNN Segmentation","created":"2018-03-26","cited_by_count":121},{"id":"1803.09693","title":"Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++","created":"2018-03-26","cited_by_count":120},{"id":"1804.01346","title":"Normalized Cut Loss for Weakly-supervised CNN Segmentation","created":"2018-04-04","cited_by_count":112},{"id":"2001.01629","title":"Deep Snake for Real-Time Instance Segmentation","created":"2020-01-06","cited_by_count":112},{"id":"1903.06874","title":"Fast Interactive Object Annotation with Curve-GCN","created":"2019-03-16","cited_by_count":95},{"id":"1912.02801","title":"PolyTransform: Deep Polygon Transformer for Instance Segmentation","created":"2019-12-05","cited_by_count":92},{"id":"1704.05548","title":"Annotating Object Instances with a Polygon-RNN","created":"2017-04-18","cited_by_count":88},{"id":"2003.10401","title":"Learning Dynamic Routing for Semantic Segmentation","created":"2020-03-23","cited_by_count":79},{"id":"2007.08921","title":"Boundary-preserving Mask R-CNN","created":"2020-07-17","cited_by_count":74},{"id":"2012.03544","title":"End-to-End Object Detection with Fully Convolutional Network","created":"2020-12-07","cited_by_count":70},{"id":"2106.02351","title":"SOLQ: Segmenting Objects by Learning Queries","created":"2021-06-04","cited_by_count":68},{"id":"2111.13673","title":"Mask Transfiner for High-Quality Instance Segmentation","created":"2021-11-26","cited_by_count":64},{"id":"2105.06464","title":"DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision","created":"2021-05-13","cited_by_count":59},{"id":"2106.04054","title":"Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation","created":"2021-06-08","cited_by_count":47},{"id":"1904.03239","title":"ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors","created":"2019-04-05","cited_by_count":43},{"id":"2207.09055","title":"Box-supervised Instance Segmentation with Level Set Evolution","created":"2022-07-19","cited_by_count":41},{"id":"1905.13417","title":"TACNet: Transition-Aware Context Network for Spatio-Temporal Action Detection","created":"2019-05-31","cited_by_count":36},{"id":"2203.10790","title":"ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformer","created":"2022-03-21","cited_by_count":36},{"id":"2203.04074","title":"E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation","created":"2022-03-08","cited_by_count":27},{"id":"1909.12513","title":"Learnable Tree Filter for Structure-preserving Feature Transform","created":"2019-09-27","cited_by_count":25},{"id":"2207.10909","title":"DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection","created":"2022-07-22","cited_by_count":25},{"id":"2301.03831","title":"Dynamic Grained Encoder for Vision Transformers","created":"2023-01-10","cited_by_count":24},{"id":"2104.01526","title":"Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images","created":"2021-04-04","cited_by_count":20},{"id":"2012.03519","title":"Fine-Grained Dynamic Head for Object Detection","created":"2020-12-07","cited_by_count":16},{"id":"2007.12387","title":"Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation","created":"2020-07-24","cited_by_count":14},{"id":"2012.03482","title":"Rethinking Learnable Tree Filter for Generic Feature Transform","created":"2020-12-07","cited_by_count":10},{"id":"2102.06777","title":"INSTA-YOLO: Real-Time Instance Segmentation","created":"2021-02-12","cited_by_count":7},{"id":"2108.04230","title":"Workshop on Autonomous Driving at CVPR 2021: Technical Report for Streaming Perception Challenge","created":"2021-07-27","cited_by_count":6},{"id":"2106.10213","title":"A Coarse-to-Fine Instance Segmentation Network with Learning Boundary Representation","created":"2021-06-18","cited_by_count":3},{"id":"2212.03517","title":"AsyInst: Asymmetric Affinity with DepthGrad and Color for Box-Supervised Instance Segmentation","created":"2022-12-07","cited_by_count":3},{"id":"2205.12646","title":"UniInst: Unique Representation for End-to-End Instance Segmentation","created":"2022-05-25","cited_by_count":2}],"next_cursor":null}