{"list":"other","total":95,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"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":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"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":"1906.05849","title":"Contrastive Multiview Coding","created":"2019-06-13","cited_by_count":1301},{"id":"1808.06670","title":"Learning deep representations by mutual information estimation and maximization","created":"2018-08-20","cited_by_count":1273},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"1603.08511","title":"Colorful Image Colorization","created":"2016-03-28","cited_by_count":1114},{"id":"1505.05192","title":"Unsupervised Visual Representation Learning by Context Prediction","created":"2015-05-19","cited_by_count":1066},{"id":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"1912.01991","title":"Self-Supervised Learning of Pretext-Invariant Representations","created":"2019-12-04","cited_by_count":808},{"id":"1906.00910","title":"Learning Representations by Maximizing Mutual Information Across Views","created":"2019-06-03","cited_by_count":734},{"id":"1905.09272","title":"Data-Efficient Image Recognition with Contrastive Predictive Coding","created":"2019-05-22","cited_by_count":673},{"id":"1902.06162","title":"Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey","created":"2019-02-16","cited_by_count":657},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"1708.03888","title":"Large Batch Training of Convolutional Networks","created":"2017-08-13","cited_by_count":535},{"id":"1911.05371","title":"Self-labelling via simultaneous clustering and representation learning","created":"2019-11-13","cited_by_count":528},{"id":"2011.09157","title":"Dense Contrastive Learning for Self-Supervised Visual Pre-Training","created":"2020-11-18","cited_by_count":512},{"id":"1411.4734","title":"Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture","created":"2014-11-18","cited_by_count":483},{"id":"2008.03800","title":"Spatiotemporal Contrastive Video Representation Learning","created":"2020-08-09","cited_by_count":372},{"id":"1602.03012","title":"EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos","created":"2016-02-09","cited_by_count":367},{"id":"1406.6909","title":"Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks","created":"2014-06-26","cited_by_count":300},{"id":"1903.07593","title":"Learning Correspondence from the Cycle-Consistency of Time","created":"2019-03-18","cited_by_count":269},{"id":"2010.09709","title":"Self-supervised Co-training for Video Representation Learning","created":"2020-10-19","cited_by_count":232},{"id":"2008.05659","title":"What Should Not Be Contrastive in Contrastive Learning","created":"2020-08-13","cited_by_count":226},{"id":"1708.01246","title":"Unsupervised Representation Learning by Sorting Sequences","created":"2017-08-03","cited_by_count":221},{"id":"1611.09842","title":"Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction","created":"2016-11-29","cited_by_count":217},{"id":"2104.14558","title":"A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning","created":"2021-04-29","cited_by_count":214},{"id":"1903.12355","title":"Local Aggregation for Unsupervised Learning of Visual Embeddings","created":"2019-03-29","cited_by_count":204},{"id":"2111.12710","title":"PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers","created":"2021-11-24","cited_by_count":204},{"id":"2103.01988","title":"Self-supervised Pretraining of Visual Features in the Wild","created":"2021-03-02","cited_by_count":198},{"id":"2004.06130","title":"SpeedNet: Learning the Speediness in Videos","created":"2020-04-13","cited_by_count":171},{"id":"1806.09594","title":"Tracking Emerges by Colorizing Videos","created":"2018-06-25","cited_by_count":166},{"id":"2103.05905","title":"VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples","created":"2021-03-10","cited_by_count":154},{"id":"1811.09795","title":"Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles","created":"2018-11-24","cited_by_count":149},{"id":"2003.10751","title":"TeCNO: Surgical Phase Recognition with Multi-Stage Temporal Convolutional Networks","created":"2020-03-24","cited_by_count":141},{"id":"2109.03223","title":"Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos","created":"2021-09-07","cited_by_count":141},{"id":"1612.06370","title":"Learning Features by Watching Objects Move","created":"2016-12-19","cited_by_count":138},{"id":"1701.06482","title":"Surgical Data Science: Enabling Next-Generation Surgery","created":"2017-01-23","cited_by_count":126},{"id":"2011.02284","title":"Surgical Data Science -- from Concepts toward Clinical Translation","created":"2020-10-30","cited_by_count":105},{"id":"2007.10730","title":"Video Representation Learning by Recognizing Temporal Transformations","created":"2020-07-21","cited_by_count":83},{"id":"1907.06099","title":"Multi-Task Recurrent Convolutional Network with Correlation Loss for Surgical Video Analysis","created":"2019-07-13","cited_by_count":76},{"id":"1711.07240","title":"MegDet: A Large Mini-Batch Object Detector","created":"2017-11-20","cited_by_count":66},{"id":"1802.01880","title":"Learning Image Representations by Completing Damaged Jigsaw Puzzles","created":"2018-02-06","cited_by_count":66},{"id":"2103.16327","title":"Temporal Memory Relation Network for Workflow Recognition from Surgical Video","created":"2021-03-30","cited_by_count":66},{"id":"2103.03873","title":"OperA: Attention-Regularized Transformers for Surgical Phase Recognition","created":"2021-03-05","cited_by_count":60},{"id":"2109.14956","title":"Comparative Validation of Machine Learning Algorithms for Surgical Workflow and Skill Analysis with the HeiChole Benchmark","created":"2021-09-30","cited_by_count":60},{"id":"2106.09157","title":"Positional Contrastive Learning for Volumetric Medical Image Segmentation","created":"2021-06-16","cited_by_count":56},{"id":"2109.07407","title":"Semi-supervised Contrastive Learning for Label-efficient Medical Image Segmentation","created":"2021-09-15","cited_by_count":52},{"id":"2106.08808","title":"Contrastive Learning with Continuous Proxy Meta-Data for 3D MRI Classification","created":"2021-06-16","cited_by_count":49},{"id":"1904.11407","title":"DynamoNet: Dynamic Action and Motion Network","created":"2019-04-25","cited_by_count":48},{"id":"1807.10565","title":"DeepPhase: Surgical Phase Recognition in CATARACTS Videos","created":"2018-07-17","cited_by_count":47},{"id":"2103.03423","title":"Constrained Contrastive Distribution Learning for Unsupervised Anomaly Detection and Localisation in Medical Images","created":"2021-03-05","cited_by_count":45},{"id":"2204.04746","title":"CholecTriplet2021: A benchmark challenge for surgical action triplet recognition","created":"2022-04-10","cited_by_count":44},{"id":"1808.07507","title":"Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognition","created":"2018-08-22","cited_by_count":40},{"id":"1812.01366","title":"Weakly Supervised Convolutional LSTM Approach for Tool Tracking in Laparoscopic Videos","created":"2018-12-04","cited_by_count":35},{"id":"2011.13066","title":"USCL: Pretraining Deep Ultrasound Image Diagnosis Model through Video Contrastive Representation Learning","created":"2020-11-25","cited_by_count":34},{"id":"2109.07504","title":"Federated Contrastive Learning for Decentralized Unlabeled Medical Images","created":"2021-09-15","cited_by_count":34},{"id":"1711.09726","title":"Exploiting the potential of unlabeled endoscopic video data with self-supervised learning","created":"2017-11-27","cited_by_count":33},{"id":"2204.10983","title":"Federated Contrastive Learning for Volumetric Medical Image Segmentation","created":"2022-04-23","cited_by_count":33},{"id":"2203.15371","title":"mc-BEiT: Multi-choice Discretization for Image BERT Pre-training","created":"2022-03-29","cited_by_count":31},{"id":"2107.08274","title":"Lesion-based Contrastive Learning for Diabetic Retinopathy Grading from Fundus Images","created":"2021-07-17","cited_by_count":25},{"id":"1805.08569","title":"Less is More: Surgical Phase Recognition with Less Annotations through Self-Supervised Pre-training of CNN-LSTM Networks","created":"2018-05-22","cited_by_count":24},{"id":"2111.10827","title":"Domain Generalization for Mammography Detection via Multi-style and Multi-view Contrastive Learning","created":"2021-11-21","cited_by_count":19},{"id":"2203.07976","title":"On the Pitfalls of Batch Normalization for End-to-End Video Learning: A Study on Surgical Workflow Analysis","created":"2022-03-15","cited_by_count":19},{"id":"2203.07345","title":"Federated Cycling (FedCy): Semi-supervised Federated Learning of Surgical Phases","created":"2022-03-14","cited_by_count":18},{"id":"2012.07043","title":"Contrastive Learning of Relative Position Regression for One-Shot Object Localization in 3D Medical Images","created":"2020-12-13","cited_by_count":17},{"id":"1806.06811","title":"Temporal coherence-based self-supervised learning for laparoscopic workflow analysis","created":"2018-06-18","cited_by_count":16},{"id":"1902.04810","title":"Self-Supervised Surgical Tool Segmentation using Kinematic Information","created":"2019-02-13","cited_by_count":15},{"id":"2008.06607","title":"Self-supervised Contrastive Video-Speech Representation Learning for Ultrasound","created":"2020-08-14","cited_by_count":15},{"id":"2107.03225","title":"Categorical Relation-Preserving Contrastive Knowledge Distillation for Medical Image Classification","created":"2021-07-07","cited_by_count":14},{"id":"2103.00586","title":"A Kinematic Bottleneck Approach For Pose Regression of Flexible Surgical Instruments directly from Images","created":"2021-02-28","cited_by_count":11},{"id":"2107.05482","title":"Anatomy-Constrained Contrastive Learning for Synthetic Segmentation without Ground-truth","created":"2021-07-12","cited_by_count":9},{"id":"1702.03684","title":"Unsupervised temporal context learning using convolutional neural networks for laparoscopic workflow analysis","created":"2017-02-13","cited_by_count":7},{"id":"2112.13815","title":"Temporally Constrained Neural Networks (TCNN): A framework for semi-supervised video semantic segmentation","created":"2021-12-27","cited_by_count":6},{"id":"2105.10310","title":"Multi-Task, Multi-Domain Deep Segmentation with Shared Representations and Contrastive Regularization for Sparse Pediatric Datasets","created":"2021-05-21","cited_by_count":5}],"next_cursor":null}