{"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":"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":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1512.02134","title":"A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation","created":"2015-12-07","cited_by_count":881},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1811.11168","title":"Deformable ConvNets v2: More Deformable, Better Results","created":"2018-11-27","cited_by_count":670},{"id":"1904.08189","title":"CenterNet: Keypoint Triplets for Object Detection","created":"2019-04-17","cited_by_count":654},{"id":"1707.03237","title":"Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations","created":"2017-07-11","cited_by_count":620},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"1903.00450","title":"Multi-Object Representation Learning with Iterative Variational Inference","created":"2019-03-01","cited_by_count":360},{"id":"2003.07853","title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","created":"2020-03-17","cited_by_count":326},{"id":"1907.13052","title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","created":"2019-07-30","cited_by_count":227},{"id":"2004.09548","title":"AANet: Adaptive Aggregation Network for Efficient Stereo Matching","created":"2020-04-20","cited_by_count":202},{"id":"2009.07378","title":"BOP Challenge 2020 on 6D Object Localization","created":"2020-09-15","cited_by_count":193},{"id":"2006.09214","title":"FCOS: A simple and strong anchor-free object detector","created":"2020-06-14","cited_by_count":171},{"id":"2010.13501","title":"Hierarchical Neural Architecture Search for Deep Stereo Matching","created":"2020-10-26","cited_by_count":166},{"id":"2003.08429","title":"STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos","created":"2020-03-18","cited_by_count":121},{"id":"1708.02551","title":"Semantic Instance Segmentation with a Discriminative Loss Function","created":"2017-08-08","cited_by_count":118},{"id":"1912.02801","title":"PolyTransform: Deep Polygon Transformer for Instance Segmentation","created":"2019-12-05","cited_by_count":92},{"id":"1906.11109","title":"Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth","created":"2019-06-26","cited_by_count":89},{"id":"1807.11699","title":"SegStereo: Exploiting Semantic Information for Disparity Estimation","created":"2018-07-31","cited_by_count":88},{"id":"2007.08073","title":"Unseen Object Instance Segmentation for Robotic Environments","created":"2020-07-16","cited_by_count":85},{"id":"1506.06204","title":"Learning to Segment Object Candidates","created":"2015-06-20","cited_by_count":79},{"id":"1611.08303","title":"Deep Watershed Transform for Instance Segmentation","created":"2016-11-24","cited_by_count":78},{"id":"1911.01911","title":"BlenderProc","created":"2019-10-25","cited_by_count":77},{"id":"1906.06565","title":"Deep Set Prediction Networks","created":"2019-06-15","cited_by_count":71},{"id":"2007.15157","title":"Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation","created":"2020-07-30","cited_by_count":64},{"id":"1902.01626","title":"EasyLabel: A Semi-Automatic Pixel-wise Object Annotation Tool for Creating Robotic RGB-D Datasets","created":"2019-02-05","cited_by_count":58},{"id":"1902.03715","title":"Towards Segmenting Anything That Moves","created":"2019-02-11","cited_by_count":51},{"id":"1809.00076","title":"3D Segmentation with Exponential Logarithmic Loss for Highly Unbalanced Object Sizes","created":"2018-08-31","cited_by_count":42},{"id":"1907.13236","title":"The Best of Both Modes: Separately Leveraging RGB and Depth for Unseen Object Instance Segmentation","created":"2019-07-30","cited_by_count":39},{"id":"2011.09763","title":"Attention-Based Transformers for Instance Segmentation of Cells in Microstructures","created":"2020-11-19","cited_by_count":38},{"id":"1509.01277","title":"A Dataset for Improved RGBD-based Object Detection and Pose Estimation for Warehouse Pick-and-Place","created":"2015-09-03","cited_by_count":35},{"id":"1812.02772","title":"Object Discovery in Videos as Foreground Motion Clustering","created":"2018-12-06","cited_by_count":32},{"id":"1910.00541","title":"Real-Time Semantic Stereo Matching","created":"2019-10-01","cited_by_count":23},{"id":"1511.08250","title":"Recurrent Instance Segmentation","created":"2015-11-25","cited_by_count":21},{"id":"1809.04734","title":"DispSegNet: Leveraging Semantics for End-to-End Learning of Disparity Estimation from Stereo Imagery","created":"2018-09-13","cited_by_count":15},{"id":"2101.08461","title":"Segmenting Transparent Object in the Wild with Transformer","created":"2021-01-21","cited_by_count":13},{"id":"1712.00617","title":"Recurrent Neural Networks for Semantic Instance Segmentation","created":"2017-12-02","cited_by_count":11},{"id":"1709.07158","title":"SceneCut: Joint Geometric and Object Segmentation for Indoor Scenes","created":"2017-09-21","cited_by_count":9},{"id":"2002.03501","title":"Segmenting Unseen Industrial Components in a Heavy Clutter Using RGB-D Fusion and Synthetic Data","created":"2020-02-10","cited_by_count":6},{"id":"1511.06449","title":"Learning to decompose for object detection and instance segmentation","created":"2015-11-19","cited_by_count":4},{"id":"2002.04487","title":"Self-Supervised Object-in-Gripper Segmentation from Robotic Motions","created":"2020-02-11","cited_by_count":4},{"id":"1808.04969","title":"Never Mind the Bounding Boxes, Here's the SAND Filters","created":"2018-08-15","cited_by_count":1}],"next_cursor":null}