{"list":"other","total":71,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"id":"1406.4729","title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","created":"2014-06-18","cited_by_count":720},{"id":"1708.00786","title":"Structure-measure: A New Way to Evaluate Foreground Maps","created":"2017-08-02","cited_by_count":480},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"id":"1611.05198","title":"One-Shot Video Object Segmentation","created":"2016-11-16","cited_by_count":235},{"id":"1809.00461","title":"YouTube-VOS: Sequence-to-Sequence Video Object Segmentation","created":"2018-09-03","cited_by_count":232},{"id":"2102.10274","title":"Concealed Object Detection","created":"2021-02-20","cited_by_count":212},{"id":"1902.09513","title":"FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation","created":"2019-02-25","cited_by_count":178},{"id":"1911.11445","title":"F3Net: Fusion, Feedback and Focus for Salient Object Detection","created":"2019-11-26","cited_by_count":176},{"id":"1612.02646","title":"Learning Video Object Segmentation from Static Images","created":"2016-12-08","cited_by_count":151},{"id":"1511.06432","title":"Delving Deeper into Convolutional Networks for Learning Video Representations","created":"2015-11-19","cited_by_count":148},{"id":"2003.08333","title":"Collaborative Video Object Segmentation by Foreground-Background Integration","created":"2020-03-18","cited_by_count":142},{"id":"2001.06810","title":"See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks","created":"2020-01-19","cited_by_count":138},{"id":"1501.02741","title":"Salient Object Detection: A Benchmark","created":"2015-01-05","cited_by_count":131},{"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":"2007.08270","title":"Kernelized Memory Network for Video Object Segmentation","created":"2020-07-16","cited_by_count":111},{"id":"2101.08833","title":"SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation","created":"2021-01-21","cited_by_count":106},{"id":"1411.5878","title":"Salient Object Detection: A Survey","created":"2014-11-18","cited_by_count":98},{"id":"1905.00737","title":"The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation","created":"2019-05-02","cited_by_count":97},{"id":"1709.06750","title":"SegFlow: Joint Learning for Video Object Segmentation and Optical Flow","created":"2017-09-20","cited_by_count":92},{"id":"2003.11540","title":"Learning What to Learn for Video Object Segmentation","created":"2020-03-25","cited_by_count":89},{"id":"2001.06807","title":"Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks","created":"2020-01-19","cited_by_count":84},{"id":"1701.05384","title":"FusionSeg: Learning to combine motion and appearance for fully automatic segmention of generic objects in videos","created":"2017-01-19","cited_by_count":77},{"id":"1612.08871","title":"Semantic Video Segmentation by Gated Recurrent Flow Propagation","created":"2016-12-28","cited_by_count":76},{"id":"2003.00908","title":"Learning Fast and Robust Target Models for Video Object Segmentation","created":"2020-02-27","cited_by_count":76},{"id":"2105.08468","title":"Progressively Normalized Self-Attention Network for Video Polyp Segmentation","created":"2021-05-18","cited_by_count":75},{"id":"2008.00230","title":"RGB-D Salient Object Detection: A Survey","created":"2020-08-01","cited_by_count":73},{"id":"1909.07061","title":"Motion Guided Attention for Video Salient Object Detection","created":"2019-09-16","cited_by_count":72},{"id":"2103.16110","title":"Kaleido-BERT: Vision-Language Pre-training on Fashion Domain","created":"2021-03-30","cited_by_count":67},{"id":"1704.05737","title":"Learning Video Object Segmentation with Visual Memory","created":"2017-04-19","cited_by_count":66},{"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":"2003.04253","title":"Motion-Attentive Transition for Zero-Shot Video Object Segmentation","created":"2020-03-09","cited_by_count":62},{"id":"1908.05786","title":"TASED-Net: Temporally-Aggregating Spatial Encoder-Decoder Network for Video Saliency Detection","created":"2019-08-15","cited_by_count":59},{"id":"1806.02323","title":"Fast and Accurate Online Video Object Segmentation via Tracking Parts","created":"2018-06-06","cited_by_count":57},{"id":"2008.11516","title":"Making a Case for 3D Convolutions for Object Segmentation in Videos","created":"2020-08-26","cited_by_count":56},{"id":"2004.07193","title":"A Transductive Approach for Video Object Segmentation","created":"2020-04-15","cited_by_count":55},{"id":"1908.04051","title":"Semi-Supervised Video Salient Object Detection Using Pseudo-Labels","created":"2019-08-12","cited_by_count":54},{"id":"2003.00482","title":"State-Aware Tracker for Real-Time Video Object Segmentation","created":"2020-03-01","cited_by_count":54},{"id":"1612.07217","title":"Learning Motion Patterns in Videos","created":"2016-12-21","cited_by_count":53},{"id":"1910.10895","title":"Anchor Diffusion for Unsupervised Video Object Segmentation","created":"2019-10-24","cited_by_count":50},{"id":"1611.07675","title":"Video Captioning with Transferred Semantic Attributes","created":"2016-11-23","cited_by_count":46},{"id":"1702.00871","title":"Video Salient Object Detection via Fully Convolutional Networks","created":"2017-02-02","cited_by_count":46},{"id":"1712.08416","title":"On the Integration of Optical Flow and Action Recognition","created":"2017-12-22","cited_by_count":42},{"id":"1804.03821","title":"ExFuse: Enhancing Feature Fusion for Semantic Segmentation","created":"2018-04-11","cited_by_count":42},{"id":"2003.13246","title":"Memory Aggregation Networks for Efficient Interactive Video Object Segmentation","created":"2020-03-30","cited_by_count":40},{"id":"1712.01127","title":"Learning to Segment Moving Objects","created":"2017-12-01","cited_by_count":39},{"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":"1911.12739","title":"Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow","created":"2019-11-28","cited_by_count":31},{"id":"2104.02391","title":"Weakly Supervised Video Salient Object Detection","created":"2021-04-06","cited_by_count":28},{"id":"1810.07733","title":"Video Object Segmentation using Teacher-Student Adaptation in a Human Robot Interaction (HRI) Setting","created":"2018-10-17","cited_by_count":27},{"id":"2007.08139","title":"Interactive Video Object Segmentation Using Global and Local Transfer Modules","created":"2020-07-16","cited_by_count":26},{"id":"1909.13258","title":"EpO-Net: Exploiting Geometric Constraints on Dense Trajectories for Motion Saliency","created":"2019-09-29","cited_by_count":22},{"id":"2103.10391","title":"Learning to Recommend Frame for Interactive Video Object Segmentation in the Wild","created":"2021-03-18","cited_by_count":18},{"id":"1809.01125","title":"Unsupervised Video Object Segmentation using Motion Saliency-Guided Spatio-Temporal Propagation","created":"2018-09-04","cited_by_count":17},{"id":"2008.09721","title":"ScribbleBox: Interactive Annotation Framework for Video Object Segmentation","created":"2020-08-22","cited_by_count":14},{"id":"1708.01447","title":"Video Salient Object Detection Using Spatiotemporal Deep Features","created":"2017-08-04","cited_by_count":11},{"id":"1607.01115","title":"Click Carving: Segmenting Objects in Video with Point Clicks","created":"2016-07-05","cited_by_count":8},{"id":"1702.08634","title":"Super-Trajectory for Video Segmentation","created":"2017-02-28","cited_by_count":4},{"id":"2003.06125","title":"Dual Temporal Memory Network for Efficient Video Object Segmentation","created":"2020-03-13","cited_by_count":3},{"id":"1707.07857","title":"Motion-Appearance Interactive Encoding for Object Segmentation in Unconstrained Videos","created":"2017-07-25","cited_by_count":1}],"next_cursor":null}