{"list":"other","total":89,"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"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":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"id":"1904.08189","title":"CenterNet: Keypoint Triplets for Object Detection","created":"2019-04-17","cited_by_count":654},{"id":"1606.09549","title":"Fully-Convolutional Siamese Networks for Object Tracking","created":"2016-06-30","cited_by_count":568},{"id":"1603.00831","title":"MOT16: A Benchmark for Multi-Object Tracking","created":"2016-03-02","cited_by_count":532},{"id":"1810.11981","title":"GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild","created":"2018-10-29","cited_by_count":475},{"id":"1812.11703","title":"SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks","created":"2018-12-31","cited_by_count":446},{"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":"1809.07845","title":"LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking","created":"2018-09-20","cited_by_count":429},{"id":"2103.15436","title":"Transformer Tracking","created":"2021-03-29","cited_by_count":412},{"id":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"2103.17154","title":"Learning Spatio-Temporal Transformer for Visual Tracking","created":"2021-03-31","cited_by_count":350},{"id":"1904.07220","title":"Learning Discriminative Model Prediction for Tracking","created":"2019-04-15","cited_by_count":344},{"id":"1803.10794","title":"TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild","created":"2018-03-28","cited_by_count":343},{"id":"2203.11991","title":"Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework","created":"2022-03-22","cited_by_count":330},{"id":"2203.11082","title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","created":"2022-03-21","cited_by_count":281},{"id":"1812.05050","title":"Fast Online Object Tracking and Segmentation: A Unifying Approach","created":"2018-12-12","cited_by_count":272},{"id":"1611.09224","title":"ECO: Efficient Convolution Operators for Tracking","created":"2016-11-28","cited_by_count":239},{"id":"1611.05198","title":"One-Shot Video Object Segmentation","created":"2016-11-16","cited_by_count":235},{"id":"2003.12565","title":"Probabilistic Regression for Visual Tracking","created":"2020-03-27","cited_by_count":231},{"id":"2106.02638","title":"Associating Objects with Transformers for Video Object Segmentation","created":"2021-06-04","cited_by_count":226},{"id":"1902.03604","title":"MOTS: Multi-Object Tracking and Segmentation","created":"2019-02-10","cited_by_count":223},{"id":"2103.11681","title":"Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking","created":"2021-03-22","cited_by_count":220},{"id":"2006.10721","title":"Ocean: Object-aware Anchor-free Tracking","created":"2020-06-18","cited_by_count":212},{"id":"1510.07945","title":"Learning Multi-Domain Convolutional Neural Networks for Visual Tracking","created":"2015-10-27","cited_by_count":209},{"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":"2305.06558","title":"Segment and Track Anything","created":"2023-05-11","cited_by_count":193},{"id":"2303.06674","title":"Universal Instance Perception as Object Discovery and Retrieval","created":"2023-03-12","cited_by_count":192},{"id":"1902.09513","title":"FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation","created":"2019-02-25","cited_by_count":178},{"id":"1911.12836","title":"Siam R-CNN: Visual Tracking by Re-Detection","created":"2019-11-28","cited_by_count":174},{"id":"1710.10000","title":"PoseTrack: A Benchmark for Human Pose Estimation and Tracking","created":"2017-10-27","cited_by_count":173},{"id":"1901.08043","title":"Bottom-up Object Detection by Grouping Extreme and Center Points","created":"2019-01-23","cited_by_count":156},{"id":"1911.07241","title":"SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking","created":"2019-11-17","cited_by_count":148},{"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":"2207.09603","title":"AiATrack: Attention in Attention for Transformer Visual Tracking","created":"2022-07-20","cited_by_count":137},{"id":"2107.01153","title":"A Survey on Deep Learning Technique for Video Segmentation","created":"2021-07-02","cited_by_count":132},{"id":"2103.16556","title":"Learning Target Candidate Association to Keep Track of What Not to Track","created":"2021-03-30","cited_by_count":131},{"id":"2112.00995","title":"SwinTrack: A Simple and Strong Baseline for Transformer Tracking","created":"2021-12-02","cited_by_count":126},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124},{"id":"2203.05328","title":"Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking","created":"2022-03-10","cited_by_count":119},{"id":"2007.07020","title":"Video Object Segmentation with Episodic Graph Memory Networks","created":"2020-07-14","cited_by_count":118},{"id":"2203.11192","title":"Transforming Model Prediction for Tracking","created":"2022-03-21","cited_by_count":117},{"id":"1706.09364","title":"Online Adaptation of Convolutional Neural Networks for Video Object Segmentation","created":"2017-06-28","cited_by_count":109},{"id":"2101.08833","title":"SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation","created":"2021-01-21","cited_by_count":106},{"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":"2004.06711","title":"Deformable Siamese Attention Networks for Visual Object Tracking","created":"2020-04-14","cited_by_count":97},{"id":"1709.06031","title":"Video Object Segmentation Without Temporal Information","created":"2017-09-18","cited_by_count":93},{"id":"2207.07078","title":"Towards Grand Unification of Object Tracking","created":"2022-07-14","cited_by_count":93},{"id":"1704.06036","title":"End-to-end representation learning for Correlation Filter based tracking","created":"2017-04-20","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":"1708.02750","title":"Extreme clicking for efficient object annotation","created":"2017-08-09","cited_by_count":81},{"id":"1807.09190","title":"PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation","created":"2018-07-24","cited_by_count":81},{"id":"2007.02024","title":"Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimation","created":"2020-07-04","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":"2204.04656","title":"Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation","created":"2022-04-10","cited_by_count":79},{"id":"2205.03806","title":"Transformer Tracking with Cyclic Shifting Window Attention","created":"2022-05-08","cited_by_count":75},{"id":"2109.11404","title":"Hierarchical Memory Matching Network for Video Object Segmentation","created":"2021-09-23","cited_by_count":72},{"id":"1911.08862","title":"D3S -- A Discriminative Single Shot Segmentation Tracker","created":"2019-11-20","cited_by_count":69},{"id":"1608.03773","title":"Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking","created":"2016-08-12","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":"2107.02156","title":"Do Different Tracking Tasks Require Different Appearance Models?","created":"2021-07-05","cited_by_count":62},{"id":"2203.01666","title":"Correlation-Aware Deep Tracking","created":"2022-03-03","cited_by_count":62},{"id":"2004.00830","title":"Tracking by Instance Detection: A Meta-Learning Approach","created":"2020-04-02","cited_by_count":61},{"id":"2108.03679","title":"Joint Inductive and Transductive Learning for Video Object Segmentation","created":"2021-08-08","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":"2203.09773","title":"Local-Global Context Aware Transformer for Language-Guided Video Segmentation","created":"2022-03-18","cited_by_count":41},{"id":"2203.11191","title":"Robust Visual Tracking by Segmentation","created":"2022-03-21","cited_by_count":38},{"id":"1708.05137","title":"Pixel-Level Matching for Video Object Segmentation using Convolutional Neural Networks","created":"2017-08-17","cited_by_count":32},{"id":"2203.15175","title":"Unified Transformer Tracker for Object Tracking","created":"2022-03-29","cited_by_count":31},{"id":"2012.01866","title":"Make One-Shot Video Object Segmentation Efficient Again","created":"2020-12-03","cited_by_count":30},{"id":"2303.12782","title":"Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation","created":"2023-03-22","cited_by_count":23},{"id":"2304.06211","title":"Boosting Video Object Segmentation via Space-time Correspondence Learning","created":"2023-04-13","cited_by_count":21},{"id":"2203.11442","title":"Scalable Video Object Segmentation with Identification Mechanism","created":"2022-03-22","cited_by_count":18},{"id":"2101.02196","title":"Generating Masks from Boxes by Mining Spatio-Temporal Consistencies in Videos","created":"2021-01-06","cited_by_count":8},{"id":"2305.04470","title":"Video Object Segmentation in Panoptic Wild Scenes","created":"2023-05-08","cited_by_count":6}],"next_cursor":null}