{"list":"other","total":60,"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1607.08022","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","created":"2016-07-27","cited_by_count":1198},{"id":"1905.09272","title":"Data-Efficient Image Recognition with Contrastive Predictive Coding","created":"2019-05-22","cited_by_count":673},{"id":"1602.07868","title":"Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks","created":"2016-02-25","cited_by_count":543},{"id":"1611.05267","title":"Temporal Convolutional Networks for Action Segmentation and Detection","created":"2016-11-16","cited_by_count":508},{"id":"1903.01945","title":"MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation","created":"2019-03-05","cited_by_count":373},{"id":"1602.03012","title":"EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos","created":"2016-02-09","cited_by_count":367},{"id":"2102.06171","title":"High-Performance Large-Scale Image Recognition Without Normalization","created":"2021-02-11","cited_by_count":360},{"id":"1705.08741","title":"Train longer, generalize better: closing the generalization gap in large batch training of neural networks","created":"2017-05-24","cited_by_count":279},{"id":"2106.02036","title":"Anticipative Video Transformer","created":"2021-06-03","cited_by_count":200},{"id":"2110.08568","title":"ASFormer: Transformer for Action Segmentation","created":"2021-10-16","cited_by_count":168},{"id":"1806.02375","title":"Understanding Batch Normalization","created":"2018-06-01","cited_by_count":159},{"id":"2003.10751","title":"TeCNO: Surgical Phase Recognition with Multi-Stage Temporal Convolutional Networks","created":"2020-03-24","cited_by_count":141},{"id":"1702.03275","title":"Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models","created":"2017-02-10","cited_by_count":128},{"id":"1701.06482","title":"Surgical Data Science: Enabling Next-Generation Surgery","created":"2017-01-23","cited_by_count":126},{"id":"2005.02190","title":"Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video","created":"2020-05-04","cited_by_count":120},{"id":"2011.02284","title":"Surgical Data Science -- from Concepts toward Clinical Translation","created":"2020-10-30","cited_by_count":105},{"id":"2103.09712","title":"Trans-SVNet: Accurate Phase Recognition from Surgical Videos via Hybrid Embedding Aggregation Transformer","created":"2021-03-17","cited_by_count":94},{"id":"2007.06866","title":"Alleviating Over-segmentation Errors by Detecting Action Boundaries","created":"2020-07-14","cited_by_count":87},{"id":"1811.07391","title":"Temporal Recurrent Networks for Online Action Detection","created":"2018-11-18","cited_by_count":80},{"id":"1707.04818","title":"RED: Reinforced Encoder-Decoder Networks for Action Anticipation","created":"2017-07-16","cited_by_count":78},{"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":"2103.16327","title":"Temporal Memory Relation Network for Workflow Recognition from Surgical Video","created":"2021-03-30","cited_by_count":66},{"id":"2008.07424","title":"Siloed Federated Learning for Multi-Centric Histopathology Datasets","created":"2020-08-17","cited_by_count":61},{"id":"2103.03873","title":"OperA: Attention-Regularized Transformers for Surgical Phase Recognition","created":"2021-03-05","cited_by_count":60},{"id":"1807.10565","title":"DeepPhase: Surgical Phase Recognition in CATARACTS Videos","created":"2018-07-17","cited_by_count":47},{"id":"1911.09737","title":"Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Networks","created":"2019-11-21","cited_by_count":45},{"id":"2004.02967","title":"Evolving Normalization-Activation Layers","created":"2020-04-06","cited_by_count":45},{"id":"2105.07576","title":"Rethinking \"Batch\" in BatchNorm","created":"2021-05-17","cited_by_count":45},{"id":"2009.01142","title":"Long-Term Anticipation of Activities with Cycle Consistency","created":"2020-09-02","cited_by_count":40},{"id":"1610.09278","title":"The TUM LapChole dataset for the M2CAI 2016 workflow challenge","created":"2016-10-28","cited_by_count":38},{"id":"1912.04461","title":"Learning to Discriminate Information for Online Action Detection","created":"2019-12-10","cited_by_count":37},{"id":"1907.11454","title":"Using 3D Convolutional Neural Networks to Learn Spatiotemporal Features for Automatic Surgical Gesture Recognition in Video","created":"2019-07-26","cited_by_count":36},{"id":"1812.01366","title":"Weakly Supervised Convolutional LSTM Approach for Tool Tracking in Laparoscopic Videos","created":"2018-12-04","cited_by_count":35},{"id":"1802.03243","title":"RSDNet: Learning to Predict Remaining Surgery Duration from Laparoscopic Videos Without Manual Annotations","created":"2018-02-09","cited_by_count":26},{"id":"2106.05956","title":"Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning","created":"2021-06-10","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":"1904.06031","title":"EvalNorm: Estimating Batch Normalization Statistics for Evaluation","created":"2019-04-12","cited_by_count":20},{"id":"2002.05712","title":"Cross-Iteration Batch Normalization","created":"2020-02-13","cited_by_count":20},{"id":"2107.04810","title":"Not End-to-End: Explore Multi-Stage Architecture for Online Surgical Phase Recognition","created":"2021-07-10","cited_by_count":20},{"id":"2001.06838","title":"Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization","created":"2020-01-19","cited_by_count":19},{"id":"2011.09158","title":"Privileged Knowledge Distillation for Online Action Detection","created":"2020-11-18","cited_by_count":18},{"id":"2106.11048","title":"CataNet: Predicting remaining cataract surgery duration","created":"2021-06-21","cited_by_count":15},{"id":"2007.00548","title":"Rethinking Anticipation Tasks: Uncertainty-aware Anticipation of Sparse Surgical Instrument Usage for Context-aware Assistance","created":"2020-07-01","cited_by_count":13},{"id":"2106.03743","title":"Proxy-Normalizing Activations to Match Batch Normalization while Removing Batch Dependence","created":"2021-06-07","cited_by_count":12},{"id":"1811.11727","title":"Future-State Predicting LSTM for Early Surgery Type Recognition","created":"2018-11-28","cited_by_count":9},{"id":"2002.11367","title":"Unsupervised Temporal Video Segmentation as an Auxiliary Task for Predicting the Remaining Surgery Duration","created":"2020-02-26","cited_by_count":7},{"id":"1811.03382","title":"Active Learning using Deep Bayesian Networks for Surgical Workflow Analysis","created":"2018-11-08","cited_by_count":6},{"id":"1811.03384","title":"Prediction of laparoscopic procedure duration using unlabeled, multimodal sensor data","created":"2018-11-08","cited_by_count":6},{"id":"2004.09845","title":"LRTD: Long-Range Temporal Dependency based Active Learning for Surgical Workflow Recognition","created":"2020-04-21","cited_by_count":6}],"next_cursor":null}