{"list":"other","total":58,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"1511.07122","title":"Multi-Scale Context Aggregation by Dilated Convolutions","created":"2015-11-23","cited_by_count":1133},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1907.10529","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","created":"2019-07-24","cited_by_count":834},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"1809.06839","title":"Albumentations: fast and flexible image augmentations","created":"2018-09-18","cited_by_count":560},{"id":"1611.05267","title":"Temporal Convolutional Networks for Action Segmentation and Detection","created":"2016-11-16","cited_by_count":508},{"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":"2004.08955","title":"ResNeSt: Split-Attention Networks","created":"2020-04-19","cited_by_count":445},{"id":"2102.10882","title":"Conditional Positional Encodings for Vision Transformers","created":"2021-02-22","cited_by_count":406},{"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":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"1411.4280","title":"Efficient Object Localization Using Convolutional Networks","created":"2014-11-16","cited_by_count":227},{"id":"2110.08568","title":"ASFormer: Transformer for Action Segmentation","created":"2021-10-16","cited_by_count":168},{"id":"2003.10751","title":"TeCNO: Surgical Phase Recognition with Multi-Stage Temporal Convolutional Networks","created":"2020-03-24","cited_by_count":141},{"id":"1712.09763","title":"PixelSNAIL: An Improved Autoregressive Generative Model","created":"2017-12-28","cited_by_count":137},{"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":"2208.02049","title":"AutoLaparo: A New Dataset of Integrated Multi-tasks for Image-guided Surgical Automation in Laparoscopic Hysterectomy","created":"2022-08-03","cited_by_count":85},{"id":"2210.10352","title":"Temporal Action Segmentation: An Analysis of Modern Techniques","created":"2022-10-19","cited_by_count":85},{"id":"2103.06104","title":"U-Net Transformer: Self and Cross Attention for Medical Image Segmentation","created":"2021-03-10","cited_by_count":81},{"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":"2305.08989","title":"LoViT: Long Video Transformer for Surgical Phase Recognition","created":"2023-05-15","cited_by_count":56},{"id":"2207.00449","title":"Dissecting Self-Supervised Learning Methods for Surgical Computer Vision","created":"2022-07-01","cited_by_count":48},{"id":"2102.12218","title":"Multi-Task Temporal Convolutional Networks for Joint Recognition of Surgical Phases and Steps in Gastric Bypass Procedures","created":"2021-02-24","cited_by_count":42},{"id":"2111.11044","title":"Exploring Segment-level Semantics for Online Phase Recognition from Surgical Videos","created":"2021-11-22","cited_by_count":23},{"id":"2212.11078","title":"C2F-TCN: A Framework for Semi and Fully Supervised Temporal Action Segmentation","created":"2022-12-20","cited_by_count":23},{"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":"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":"1806.06811","title":"Temporal coherence-based self-supervised learning for laparoscopic workflow analysis","created":"2018-06-18","cited_by_count":16},{"id":"2305.13961","title":"Metrics Matter in Surgical Phase Recognition","created":"2023-05-23","cited_by_count":14},{"id":"2202.07790","title":"Speech Denoising in the Waveform Domain with Self-Attention","created":"2022-02-15","cited_by_count":13},{"id":"2205.02805","title":"An Empirical Study on Activity Recognition in Long Surgical Videos","created":"2022-05-05","cited_by_count":13},{"id":"2205.13425","title":"Do we really need temporal convolutions in action segmentation?","created":"2022-05-26","cited_by_count":10},{"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":"2208.00902","title":"Retrieval of surgical phase transitions using reinforcement learning","created":"2022-08-01","cited_by_count":7},{"id":"2203.09230","title":"Surgical Workflow Recognition: from Analysis of Challenges to Architectural Study","created":"2022-03-17","cited_by_count":6}],"next_cursor":null}