{"list":"other","total":83,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"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":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"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":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"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":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"1904.02689","title":"YOLACT: Real-time Instance Segmentation","created":"2019-04-04","cited_by_count":443},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"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":"2302.13848","title":"ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation","created":"2023-02-27","cited_by_count":416},{"id":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"id":"1910.04751","title":"Panoptic-DeepLab","created":"2019-10-10","cited_by_count":363},{"id":"2212.05199","title":"MAGVIT: Masked Generative Video Transformer","created":"2022-12-10","cited_by_count":346},{"id":"2206.02777","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","created":"2022-06-06","cited_by_count":344},{"id":"2305.13077","title":"ControlVideo: Training-free Controllable Text-to-Video Generation","created":"2023-05-22","cited_by_count":327},{"id":"2311.16518","title":"SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution","created":"2023-11-27","cited_by_count":315},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294},{"id":"1912.02315","title":"12-in-1: Multi-Task Vision and Language Representation Learning","created":"2019-12-05","cited_by_count":278},{"id":"2302.01872","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","created":"2023-02-03","cited_by_count":234},{"id":"1809.00461","title":"YouTube-VOS: Sequence-to-Sequence Video Object Segmentation","created":"2018-09-03","cited_by_count":232},{"id":"2006.06664","title":"Quasi-Dense Similarity Learning for Multiple Object Tracking","created":"2020-06-11","cited_by_count":220},{"id":"2006.14822","title":"A survey of loss functions for semantic segmentation","created":"2020-06-26","cited_by_count":217},{"id":"2106.14855","title":"K-Net: Towards Unified Image Segmentation","created":"2021-06-28","cited_by_count":212},{"id":"2303.08131","title":"A Simple Framework for Open-Vocabulary Segmentation and Detection","created":"2023-03-14","cited_by_count":198},{"id":"2303.06674","title":"Universal Instance Perception as Object Discovery and Retrieval","created":"2023-03-12","cited_by_count":192},{"id":"2103.16562","title":"Boundary IoU: Improving Object-Centric Image Segmentation Evaluation","created":"2021-03-30","cited_by_count":188},{"id":"2310.12982","title":"Putting the Object Back into Video Object Segmentation","created":"2023-10-19","cited_by_count":188},{"id":"2307.04767","title":"Semantic-SAM: Segment and Recognize Anything at Any Granularity","created":"2023-07-10","cited_by_count":185},{"id":"2201.00487","title":"Language as Queries for Referring Video Object Segmentation","created":"2022-01-03","cited_by_count":182},{"id":"2112.10764","title":"Mask2Former for Video Instance Segmentation","created":"2021-12-20","cited_by_count":171},{"id":"1603.04042","title":"Deep Interactive Object Selection","created":"2016-03-13","cited_by_count":160},{"id":"2210.09782","title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","created":"2022-10-18","cited_by_count":148},{"id":"2006.11339","title":"Video Panoptic Segmentation","created":"2020-06-19","cited_by_count":142},{"id":"1711.09081","title":"Deep Extreme Cut: From Extreme Points to Object Segmentation","created":"2017-11-24","cited_by_count":127},{"id":"2112.08275","title":"SeqFormer: Sequential Transformer for Video Instance Segmentation","created":"2021-12-15","cited_by_count":98},{"id":"2207.10661","title":"In Defense of Online Models for Video Instance Segmentation","created":"2022-07-21","cited_by_count":97},{"id":"2303.17225","title":"FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation","created":"2023-03-30","cited_by_count":95},{"id":"2206.04403","title":"VITA: Video Instance Segmentation via Object Token Association","created":"2022-06-09","cited_by_count":94},{"id":"2208.02245","title":"MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training","created":"2022-08-03","cited_by_count":94},{"id":"2012.00720","title":"Fully Convolutional Networks for Panoptic Segmentation","created":"2020-12-01","cited_by_count":92},{"id":"1712.01892","title":"Grounding Referring Expressions in Images by Variational Context","created":"2017-12-05","cited_by_count":82},{"id":"2204.00822","title":"Semantic-Aware Domain Generalized Segmentation","created":"2022-04-02","cited_by_count":79},{"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":"2306.03413","title":"DVIS: Decoupled Video Instance Segmentation Framework","created":"2023-06-06","cited_by_count":77},{"id":"2102.11859","title":"STEP: Segmenting and Tracking Every Pixel","created":"2021-02-23","cited_by_count":73},{"id":"2209.12118","title":"BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video","created":"2022-09-25","cited_by_count":66},{"id":"1902.05093","title":"DeeperLab: Single-Shot Image Parser","created":"2019-02-13","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":"2307.09356","title":"OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation","created":"2023-07-18","cited_by_count":62},{"id":"2211.08834","title":"A Generalized Framework for Video Instance Segmentation","created":"2022-11-16","cited_by_count":53},{"id":"2307.13537","title":"Spectrum-guided Multi-granularity Referring Video Object Segmentation","created":"2023-07-25","cited_by_count":48},{"id":"2104.05606","title":"Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation","created":"2021-04-06","cited_by_count":42},{"id":"2205.15361","title":"TubeFormer-DeepLab: Video Mask Transformer","created":"2022-05-30","cited_by_count":35},{"id":"2301.02657","title":"TarViS: A Unified Approach for Target-based Video Segmentation","created":"2023-01-06","cited_by_count":33},{"id":"2107.00057","title":"Simple Training Strategies and Model Scaling for Object Detection","created":"2021-06-30","cited_by_count":25},{"id":"2305.16835","title":"OpenVIS: Open-vocabulary Video Instance Segmentation","created":"2023-05-26","cited_by_count":25},{"id":"2304.04694","title":"Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentation","created":"2023-04-10","cited_by_count":24},{"id":"2312.15715","title":"UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces","created":"2023-12-25","cited_by_count":22},{"id":"2401.00877","title":"Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolution","created":"2023-12-30","cited_by_count":15},{"id":"2302.14578","title":"Interactive Segmentation as Gaussian Process Classification","created":"2023-02-28","cited_by_count":14},{"id":"2303.14395","title":"MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos","created":"2023-03-25","cited_by_count":13},{"id":"2303.11567","title":"One-to-Few Label Assignment for End-to-End Dense Detection","created":"2023-03-21","cited_by_count":8},{"id":"2312.06703","title":"OpenSD: Unified Open-Vocabulary Segmentation and Detection","created":"2023-12-10","cited_by_count":7},{"id":"2305.04470","title":"Video Object Segmentation in Panoptic Wild Scenes","created":"2023-05-08","cited_by_count":6}],"next_cursor":null}