{"list":"other","total":89,"rows":[{"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":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"2207.07115","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","created":"2022-07-14","cited_by_count":439},{"id":"1904.00607","title":"Video Object Segmentation using Space-Time Memory Networks","created":"2019-04-01","cited_by_count":438},{"id":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"id":"1812.05050","title":"Fast Online Object Tracking and Segmentation: A Unifying Approach","created":"2018-12-12","cited_by_count":272},{"id":"2108.05565","title":"Vision-Language Transformer and Query Generation for Referring Segmentation","created":"2021-08-12","cited_by_count":240},{"id":"2006.14613","title":"Space-Time Correspondence as a Contrastive Random Walk","created":"2020-06-25","cited_by_count":239},{"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":"2106.02638","title":"Associating Objects with Transformers for Video Object Segmentation","created":"2021-06-04","cited_by_count":226},{"id":"2106.05210","title":"Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation","created":"2021-06-09","cited_by_count":203},{"id":"1902.09513","title":"FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation","created":"2019-02-25","cited_by_count":178},{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154},{"id":"1612.02646","title":"Learning Video Object Segmentation from Static Images","created":"2016-12-08","cited_by_count":151},{"id":"2210.09782","title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","created":"2022-10-18","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":"2006.11339","title":"Video Panoptic Segmentation","created":"2020-06-19","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":"2111.14821","title":"End-to-End Referring Video Object Segmentation with Multimodal Transformers","created":"2021-11-29","cited_by_count":135},{"id":"2107.01153","title":"A Survey on Deep Learning Technique for Video Segmentation","created":"2021-07-02","cited_by_count":132},{"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":"2003.08429","title":"STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos","created":"2020-03-18","cited_by_count":121},{"id":"2007.07020","title":"Video Object Segmentation with Episodic Graph Memory Networks","created":"2020-07-14","cited_by_count":118},{"id":"2210.15871","title":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation","created":"2022-10-28","cited_by_count":111},{"id":"2002.07793","title":"MAST: A Memory-Augmented Self-supervised Tracker","created":"2020-02-18","cited_by_count":109},{"id":"1909.00179","title":"Boundary-Aware Feature Propagation for Scene Segmentation","created":"2019-08-31","cited_by_count":107},{"id":"2101.08833","title":"SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation","created":"2021-01-21","cited_by_count":106},{"id":"2103.12340","title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","created":"2021-03-23","cited_by_count":104},{"id":"2105.07175","title":"Cross-Modal Progressive Comprehension for Referring Segmentation","created":"2021-05-15","cited_by_count":102},{"id":"1905.00737","title":"The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation","created":"2019-05-02","cited_by_count":97},{"id":"2004.02788","title":"Self-Supervised Scene De-occlusion","created":"2020-04-06","cited_by_count":96},{"id":"2012.05258","title":"ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation","created":"2020-12-09","cited_by_count":96},{"id":"1709.06750","title":"SegFlow: Joint Learning for Video Object Segmentation and Optical Flow","created":"2017-09-20","cited_by_count":92},{"id":"1903.05612","title":"RVOS: End-to-End Recurrent Network for Video Object Segmentation","created":"2019-03-13","cited_by_count":88},{"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":"1902.00749","title":"Online Multi-Object Tracking with Dual Matching Attention Networks","created":"2019-02-02","cited_by_count":77},{"id":"1804.03131","title":"Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learning","created":"2018-04-09","cited_by_count":74},{"id":"1904.11489","title":"Spatial-Temporal Relation Networks for Multi-Object Tracking","created":"2019-04-25","cited_by_count":74},{"id":"1909.07061","title":"Motion Guided Attention for Video Salient Object Detection","created":"2019-09-16","cited_by_count":72},{"id":"2107.02112","title":"Recovering the Unbiased Scene Graphs from the Biased Ones","created":"2021-07-05","cited_by_count":71},{"id":"1704.05737","title":"Learning Video Object Segmentation with Visual Memory","created":"2017-04-19","cited_by_count":66},{"id":"2104.04329","title":"Learning Position and Target Consistency for Memory-based Video Object Segmentation","created":"2021-04-09","cited_by_count":63},{"id":"1711.07752","title":"Repulsion Loss: Detecting Pedestrians in a Crowd","created":"2017-11-21","cited_by_count":62},{"id":"1909.02651","title":"Semantic Correlation Promoted Shape-Variant Context for Segmentation","created":"2019-09-05","cited_by_count":61},{"id":"1908.06647","title":"RANet: Ranking Attention Network for Fast Video Object Segmentation","created":"2019-08-19","cited_by_count":60},{"id":"1807.08407","title":"Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd","created":"2018-07-23","cited_by_count":58},{"id":"1806.02323","title":"Fast and Accurate Online Video Object Segmentation via Tracking Parts","created":"2018-06-06","cited_by_count":57},{"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":"2205.03761","title":"Recurrent Dynamic Embedding for Video Object Segmentation","created":"2022-05-08","cited_by_count":52},{"id":"1910.10895","title":"Anchor Diffusion for Unsupervised Video Object Segmentation","created":"2019-10-24","cited_by_count":50},{"id":"2206.03789","title":"Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation","created":"2022-06-08","cited_by_count":50},{"id":"1708.02843","title":"Online Multi-Object Tracking Using CNN-based Single Object Tracker with Spatial-Temporal Attention Mechanism","created":"2017-08-09","cited_by_count":48},{"id":"1612.05478","title":"Video Propagation Networks","created":"2016-12-16","cited_by_count":45},{"id":"2204.12109","title":"Instance-Specific Feature Propagation for Referring Segmentation","created":"2022-04-26","cited_by_count":45},{"id":"2207.12978","title":"Tracking Every Thing in the Wild","created":"2022-07-26","cited_by_count":44},{"id":"2003.05020","title":"Learning Video Object Segmentation from Unlabeled Videos","created":"2020-03-10","cited_by_count":42},{"id":"2106.01061","title":"Rethinking Cross-modal Interaction from a Top-down Perspective for Referring Video Object Segmentation","created":"2021-06-02","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":"2006.15538","title":"Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition under Occlusion","created":"2020-06-28","cited_by_count":38},{"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":"1904.09791","title":"Fast User-Guided Video Object Segmentation by Interaction-and-Propagation Networks","created":"2019-04-22","cited_by_count":33},{"id":"1708.05137","title":"Pixel-Level Matching for Video Object Segmentation using Convolutional Neural Networks","created":"2017-08-17","cited_by_count":32},{"id":"2012.02534","title":"F2Net: Learning to Focus on the Foreground for Unsupervised Video Object Segmentation","created":"2020-12-04","cited_by_count":32},{"id":"1906.05896","title":"Learning Instance Occlusion for Panoptic Segmentation","created":"2019-06-13","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":"2012.11655","title":"Learning Dynamic Network Using a Reuse Gate Function in Semi-supervised Video Object Segmentation","created":"2020-12-21","cited_by_count":28},{"id":"2102.04762","title":"Referring Segmentation in Images and Videos with Cross-Modal Self-Attention Network","created":"2021-02-09","cited_by_count":28},{"id":"2207.14012","title":"Video Mask Transfiner for High-Quality Video Instance Segmentation","created":"2022-07-28","cited_by_count":28},{"id":"1901.04877","title":"Feature Boosting Network For 3D Pose Estimation","created":"2019-01-15","cited_by_count":26},{"id":"2007.08139","title":"Interactive Video Object Segmentation Using Global and Local Transfer Modules","created":"2020-07-16","cited_by_count":26},{"id":"2208.10128","title":"SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization","created":"2022-08-22","cited_by_count":26},{"id":"2106.09453","title":"Learning to Associate Every Segment for Video Panoptic Segmentation","created":"2021-06-17","cited_by_count":25},{"id":"2004.07538","title":"Fast Template Matching and Update for Video Object Tracking and Segmentation","created":"2020-04-16","cited_by_count":24},{"id":"2204.03330","title":"Learning Local and Global Temporal Contexts for Video Semantic Segmentation","created":"2022-04-07","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},{"id":"1904.08141","title":"MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation","created":"2019-04-17","cited_by_count":20},{"id":"2207.10258","title":"Region Aware Video Object Segmentation with Deep Motion Modeling","created":"2022-07-21","cited_by_count":19},{"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":"2002.08694","title":"Bi-directional Dermoscopic Feature Learning and Multi-scale Consistent Decision Fusion for Skin Lesion Segmentation","created":"2020-02-20","cited_by_count":15},{"id":"2008.09721","title":"ScribbleBox: Interactive Annotation Framework for Video Object Segmentation","created":"2020-08-22","cited_by_count":14},{"id":"2107.13155","title":"Improving Video Instance Segmentation via Temporal Pyramid Routing","created":"2021-07-28","cited_by_count":13}],"next_cursor":null}