{"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"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":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"1602.03012","title":"EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos","created":"2016-02-09","cited_by_count":367},{"id":"1609.08675","title":"YouTube-8M: A Large-Scale Video Classification Benchmark","created":"2016-09-27","cited_by_count":324},{"id":"1604.06182","title":"The THUMOS Challenge on Action Recognition for Videos \"in the Wild\"","created":"2016-04-21","cited_by_count":213},{"id":"1902.06426","title":"2017 Robotic Instrument Segmentation Challenge","created":"2019-02-18","cited_by_count":168},{"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":"1701.06482","title":"Surgical Data Science: Enabling Next-Generation Surgery","created":"2017-01-23","cited_by_count":126},{"id":"2206.15255","title":"Neural Rendering for Stereo 3D Reconstruction of Deformable Tissues in Robotic Surgery","created":"2022-06-30","cited_by_count":123},{"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":"1507.05738","title":"Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos","created":"2015-07-21","cited_by_count":93},{"id":"2005.00214","title":"The AVA-Kinetics Localized Human Actions Video Dataset","created":"2020-05-01","cited_by_count":82},{"id":"1803.01207","title":"Automatic Instrument Segmentation in Robot-Assisted Surgery Using Deep Learning","created":"2018-03-03","cited_by_count":81},{"id":"2007.05533","title":"ISINet: An Instance-Based Approach for Surgical Instrument Segmentation","created":"2020-07-10","cited_by_count":67},{"id":"2007.05405","title":"Recognition of Instrument-Tissue Interactions in Endoscopic Videos via Action Triplets","created":"2020-07-10","cited_by_count":66},{"id":"1907.07899","title":"Incorporating Temporal Prior from Motion Flow for Instrument Segmentation in Minimally Invasive Surgery Video","created":"2019-07-18","cited_by_count":64},{"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":"1807.10565","title":"DeepPhase: Surgical Phase Recognition in CATARACTS Videos","created":"2018-07-17","cited_by_count":47},{"id":"2005.03501","title":"Heidelberg Colorectal Data Set for Surgical Data Science in the Sensor Operating Room","created":"2020-05-07","cited_by_count":47},{"id":"2202.08453","title":"TraSeTR: Track-to-Segment Transformer with Contrastive Query for Instance-level Instrument Segmentation in Robotic Surgery","created":"2022-02-17","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":"2104.03178","title":"The SARAS Endoscopic Surgeon Action Detection (ESAD) dataset: Challenges and methods","created":"2021-04-07","cited_by_count":38},{"id":"1805.02475","title":"Comparative evaluation of instrument segmentation and tracking methods in minimally invasive surgery","created":"2018-05-07","cited_by_count":37},{"id":"2303.09514","title":"MATIS: Masked-Attention Transformers for Surgical Instrument Segmentation","created":"2023-03-16","cited_by_count":36},{"id":"2006.16166","title":"Automatic Operating Room Surgical Activity Recognition for Robot-Assisted Surgery","created":"2020-06-29","cited_by_count":34},{"id":"1706.08126","title":"ToolNet: Holistically-Nested Real-Time Segmentation of Robotic Surgical Tools","created":"2017-06-25","cited_by_count":30},{"id":"2007.03357","title":"Learning and Reasoning with the Graph Structure Representation in Robotic Surgery","created":"2020-07-07","cited_by_count":29},{"id":"2201.11957","title":"Global-Reasoned Multi-Task Learning Model for Surgical Scene Understanding","created":"2022-01-28","cited_by_count":29},{"id":"2103.13111","title":"MIcro-Surgical Anastomose Workflow recognition challenge report","created":"2021-03-24","cited_by_count":28},{"id":"2211.16963","title":"Rendezvous in Time: An Attention-based Temporal Fusion approach for Surgical Triplet Recognition","created":"2022-11-30","cited_by_count":27},{"id":"2111.11044","title":"Exploring Segment-level Semantics for Online Phase Recognition from Surgical Videos","created":"2021-11-22","cited_by_count":23},{"id":"2204.05235","title":"Data Splits and Metrics for Method Benchmarking on Surgical Action Triplet Datasets","created":"2022-04-11","cited_by_count":23},{"id":"2307.09548","title":"Surgical Action Triplet Detection by Mixed Supervised Learning of Instrument-Tissue Interactions","created":"2023-07-18","cited_by_count":23},{"id":"2112.07219","title":"A real-time spatiotemporal AI model analyzes skill in open surgical videos","created":"2021-12-14","cited_by_count":11}],"next_cursor":null}