{"list":"other","total":53,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"1603.09246","title":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles","created":"2016-03-30","cited_by_count":1382},{"id":"1603.08511","title":"Colorful Image Colorization","created":"2016-03-28","cited_by_count":1114},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1512.02134","title":"A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation","created":"2015-12-07","cited_by_count":881},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"2005.10243","title":"What Makes for Good Views for Contrastive Learning?","created":"2020-05-20","cited_by_count":846},{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675},{"id":"1807.06653","title":"Invariant Information Clustering for Unsupervised Image Classification and Segmentation","created":"2018-07-17","cited_by_count":455},{"id":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"2203.08414","title":"Unsupervised Semantic Segmentation by Distilling Feature Correspondences","created":"2022-03-16","cited_by_count":241},{"id":"2109.14279","title":"Localizing Objects with Self-Supervised Transformers and no Labels","created":"2021-09-29","cited_by_count":230},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"2102.06191","title":"Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals","created":"2021-02-11","cited_by_count":190},{"id":"2202.11539","title":"Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut","created":"2022-02-23","cited_by_count":167},{"id":"2103.17070","title":"PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering","created":"2021-03-30","cited_by_count":163},{"id":"2205.07839","title":"Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization","created":"2022-05-16","cited_by_count":150},{"id":"2104.07658","title":"Self-supervised Video Object Segmentation by Motion Grouping","created":"2021-04-15","cited_by_count":147},{"id":"2104.04691","title":"Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation","created":"2021-04-10","cited_by_count":133},{"id":"1906.11883","title":"Unsupervised Learning of Object Keypoints for Perception and Control","created":"2019-06-19","cited_by_count":109},{"id":"1910.06962","title":"SegSort: Segmentation by Discriminative Sorting of Segments","created":"2019-10-15","cited_by_count":96},{"id":"2204.13101","title":"Self-Supervised Learning of Object Parts for Semantic Segmentation","created":"2022-04-27","cited_by_count":90},{"id":"1905.13539","title":"Unsupervised Object Segmentation by Redrawing","created":"2019-05-27","cited_by_count":74},{"id":"1501.06170","title":"Unsupervised Object Discovery and Localization in the Wild: Part-based Matching with Bottom-up Region Proposals","created":"2015-01-25","cited_by_count":69},{"id":"2007.02662","title":"Toward unsupervised, multi-object discovery in large-scale image collections","created":"2020-07-06","cited_by_count":65},{"id":"1806.10206","title":"Deep Feature Factorization For Concept Discovery","created":"2018-06-26","cited_by_count":64},{"id":"2012.03044","title":"Self-Supervised Visual Representation Learning from Hierarchical Grouping","created":"2020-12-05","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":"2106.06650","title":"Large-Scale Unsupervised Object Discovery","created":"2021-06-12","cited_by_count":54},{"id":"2206.06363","title":"Discovering Object Masks with Transformers for Unsupervised Semantic Segmentation","created":"2022-06-13","cited_by_count":54},{"id":"2111.06394","title":"The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos","created":"2021-11-11","cited_by_count":45},{"id":"1511.06811","title":"Learning visual groups from co-occurrences in space and time","created":"2015-11-21","cited_by_count":42},{"id":"2205.07844","title":"Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motion","created":"2022-05-16","cited_by_count":42},{"id":"2204.11432","title":"Unsupervised Hierarchical Semantic Segmentation with Multiview Cosegmentation and Clustering Transformers","created":"2022-04-25","cited_by_count":39},{"id":"1807.05636","title":"Cross Pixel Optical Flow Similarity for Self-Supervised Learning","created":"2018-07-15","cited_by_count":21},{"id":"1903.11412","title":"Self-Supervised Learning via Conditional Motion Propagation","created":"2019-03-27","cited_by_count":20},{"id":"1902.09968","title":"Object Discovery From a Single Unlabeled Image by Mining Frequent Itemset With Multi-scale Features","created":"2019-02-26","cited_by_count":19}],"next_cursor":null}