{"list":"other","total":69,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1709.02371","title":"PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume","created":"2017-09-07","cited_by_count":968},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"1606.09549","title":"Fully-Convolutional Siamese Networks for Object Tracking","created":"2016-06-30","cited_by_count":568},{"id":"1906.05909","title":"Stand-Alone Self-Attention in Vision Models","created":"2019-06-13","cited_by_count":542},{"id":"1603.00831","title":"MOT16: A Benchmark for Multi-Object Tracking","created":"2016-03-02","cited_by_count":532},{"id":"1908.06391","title":"PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment","created":"2019-08-18","cited_by_count":449},{"id":"1904.00607","title":"Video Object Segmentation using Space-Time Memory Networks","created":"2019-04-01","cited_by_count":438},{"id":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"1812.05050","title":"Fast Online Object Tracking and Segmentation: A Unifying Approach","created":"2018-12-12","cited_by_count":272},{"id":"1611.05198","title":"One-Shot Video Object Segmentation","created":"2016-11-16","cited_by_count":235},{"id":"1908.01998","title":"Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector","created":"2019-08-06","cited_by_count":206},{"id":"1902.09513","title":"FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation","created":"2019-02-25","cited_by_count":178},{"id":"2006.04710","title":"The Lipschitz Constant of Self-Attention","created":"2020-06-08","cited_by_count":174},{"id":"1907.12347","title":"FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation","created":"2019-07-29","cited_by_count":160},{"id":"1612.02646","title":"Learning Video Object Segmentation from Static Images","created":"2016-12-08","cited_by_count":151},{"id":"2005.10356","title":"TAO: A Large-Scale Benchmark for Tracking Any Object","created":"2020-05-20","cited_by_count":147},{"id":"2003.08333","title":"Collaborative Video Object Segmentation by Foreground-Background Integration","created":"2020-03-18","cited_by_count":142},{"id":"2103.07941","title":"Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion","created":"2021-03-14","cited_by_count":129},{"id":"2007.07020","title":"Video Object Segmentation with Episodic Graph Memory Networks","created":"2020-07-14","cited_by_count":118},{"id":"2005.02551","title":"CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement","created":"2020-05-06","cited_by_count":113},{"id":"2007.08270","title":"Kernelized Memory Network for Video Object Segmentation","created":"2020-07-16","cited_by_count":111},{"id":"1706.09364","title":"Online Adaptation of Convolutional Neural Networks for Video Object Segmentation","created":"2017-06-28","cited_by_count":109},{"id":"2002.07793","title":"MAST: A Memory-Augmented Self-supervised Tracker","created":"2020-02-18","cited_by_count":109},{"id":"2010.07958","title":"Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement","created":"2020-10-15","cited_by_count":101},{"id":"1802.01218","title":"Efficient Video Object Segmentation via Network Modulation","created":"2018-02-04","cited_by_count":98},{"id":"1709.06031","title":"Video Object Segmentation Without Temporal Information","created":"2017-09-18","cited_by_count":93},{"id":"1908.07274","title":"Towards High-Resolution Salient Object Detection","created":"2019-08-20","cited_by_count":92},{"id":"1809.01123","title":"VideoMatch: Matching based Video Object Segmentation","created":"2018-09-04","cited_by_count":90},{"id":"2003.11540","title":"Learning What to Learn for Video Object Segmentation","created":"2020-03-25","cited_by_count":89},{"id":"1903.05612","title":"RVOS: End-to-End Recurrent Network for Video Object Segmentation","created":"2019-03-13","cited_by_count":88},{"id":"2103.12934","title":"Efficient Regional Memory Network for Video Object Segmentation","created":"2021-03-24","cited_by_count":86},{"id":"1807.09190","title":"PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation","created":"2018-07-24","cited_by_count":81},{"id":"2010.06349","title":"Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration","created":"2020-10-13","cited_by_count":81},{"id":"1911.01911","title":"BlenderProc","created":"2019-10-25","cited_by_count":77},{"id":"2003.00908","title":"Learning Fast and Robust Target Models for Video Object Segmentation","created":"2020-02-27","cited_by_count":76},{"id":"1804.03131","title":"Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learning","created":"2018-04-09","cited_by_count":74},{"id":"2102.04604","title":"SwiftNet: Real-time Video Object Segmentation","created":"2021-02-09","cited_by_count":67},{"id":"1811.11611","title":"A Generative Appearance Model for End-to-end Video Object Segmentation","created":"2018-11-28","cited_by_count":66},{"id":"2001.11243","title":"Fast Video Object Segmentation using the Global Context Module","created":"2020-01-30","cited_by_count":65},{"id":"2104.04329","title":"Learning Position and Target Consistency for Memory-based Video Object Segmentation","created":"2021-04-09","cited_by_count":63},{"id":"1712.06861","title":"End-to-end weakly-supervised semantic alignment","created":"2017-12-19","cited_by_count":60},{"id":"1908.06647","title":"RANet: Ranking Attention Network for Fast Video Object Segmentation","created":"2019-08-19","cited_by_count":60},{"id":"1806.02323","title":"Fast and Accurate Online Video Object Segmentation via Tracking Parts","created":"2018-06-06","cited_by_count":57},{"id":"1803.04242","title":"Video Object Segmentation with Joint Re-identification and Attention-Aware Mask Propagation","created":"2018-03-12","cited_by_count":56},{"id":"2004.07193","title":"A Transductive Approach for Video Object Segmentation","created":"2020-04-15","cited_by_count":55},{"id":"2003.00482","title":"State-Aware Tracker for Real-Time Video Object Segmentation","created":"2020-03-01","cited_by_count":54},{"id":"1705.04043","title":"SCNet: Learning Semantic Correspondence","created":"2017-05-11","cited_by_count":48},{"id":"1803.09453","title":"CNN in MRF: Video Object Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRF","created":"2018-03-26","cited_by_count":48},{"id":"1803.11187","title":"MaskRNN: Instance Level Video Object Segmentation","created":"2018-03-29","cited_by_count":48},{"id":"2007.05687","title":"Fast Video Object Segmentation With Temporal Aggregation Network and Dynamic Template Matching","created":"2020-07-11","cited_by_count":37},{"id":"2012.01866","title":"Make One-Shot Video Object Segmentation Efficient Again","created":"2020-12-03","cited_by_count":30},{"id":"1910.00132","title":"CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing","created":"2019-09-30","cited_by_count":29},{"id":"1411.1091","title":"Do Convnets Learn Correspondence?","created":"2014-11-04","cited_by_count":28},{"id":"2007.08139","title":"Interactive Video Object Segmentation Using Global and Local Transfer Modules","created":"2020-07-16","cited_by_count":26},{"id":"1904.02363","title":"Spatiotemporal CNN for Video Object Segmentation","created":"2019-04-04","cited_by_count":24},{"id":"2104.10386","title":"Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps","created":"2021-04-21","cited_by_count":21}],"next_cursor":null}