{"list":"other","total":66,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"1506.04214","title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","created":"2015-06-13","cited_by_count":1436},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"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":"2003.09003","title":"MOT20: A benchmark for multi object tracking in crowded scenes","created":"2020-03-19","cited_by_count":357},{"id":"1702.05448","title":"Learning to Detect Human-Object Interactions","created":"2017-02-17","cited_by_count":240},{"id":"1902.03604","title":"MOTS: Multi-Object Tracking and Segmentation","created":"2019-02-10","cited_by_count":223},{"id":"1704.07333","title":"Detecting and Recognizing Human-Object Interactions","created":"2017-04-24","cited_by_count":199},{"id":"1505.04474","title":"Visual Semantic Role Labeling","created":"2015-05-17","cited_by_count":190},{"id":"1808.07962","title":"Learning Human-Object Interactions by Graph Parsing Neural Networks","created":"2018-08-23","cited_by_count":176},{"id":"1902.06426","title":"2017 Robotic Instrument Segmentation Challenge","created":"2019-02-18","cited_by_count":168},{"id":"2103.05399","title":"QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information","created":"2021-03-09","cited_by_count":147},{"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":"2103.04503","title":"End-to-End Human Object Interaction Detection with HOI Transformer","created":"2021-03-08","cited_by_count":135},{"id":"2001.11190","title":"2018 Robotic Scene Segmentation Challenge","created":"2020-01-30","cited_by_count":124},{"id":"1503.01313","title":"A Novel Performance Evaluation Methodology for Single-Target Trackers","created":"2015-03-04","cited_by_count":113},{"id":"2012.12453","title":"CholecSeg8k: A Semantic Segmentation Dataset for Laparoscopic Cholecystectomy Based on Cholec80","created":"2020-12-23","cited_by_count":106},{"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":"2112.01838","title":"Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer","created":"2021-12-03","cited_by_count":91},{"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":"2012.02994","title":"Attention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition","created":"2020-12-05","cited_by_count":80},{"id":"2007.05405","title":"Recognition of Instrument-Tissue Interactions in Endoscopic Videos via Action Triplets","created":"2020-07-10","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":"1910.05121","title":"Methods and open-source toolkit for analyzing and visualizing challenge results","created":"2019-10-11","cited_by_count":60},{"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":"1802.08774","title":"Tool Detection and Operative Skill Assessment in Surgical Videos Using Region-Based Convolutional Neural Networks","created":"2018-02-24","cited_by_count":57},{"id":"1910.04071","title":"BIAS: Transparent reporting of biomedical image analysis challenges","created":"2019-10-09","cited_by_count":57},{"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":"2204.04746","title":"CholecTriplet2021: A benchmark challenge for surgical action triplet recognition","created":"2022-04-10","cited_by_count":44},{"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":"2112.03902","title":"MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection","created":"2021-12-07","cited_by_count":42},{"id":"1910.09031","title":"CAI4CAI: The Rise of Contextual Artificial Intelligence in Computer Assisted Interventions","created":"2019-10-20","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":"1812.01366","title":"Weakly Supervised Convolutional LSTM Approach for Tool Tracking in Laparoscopic Videos","created":"2018-12-04","cited_by_count":35},{"id":"2108.00873","title":"Shallow Feature Matters for Weakly Supervised Object Localization","created":"2021-08-02","cited_by_count":34},{"id":"2103.13111","title":"MIcro-Surgical Anastomose Workflow recognition challenge report","created":"2021-03-24","cited_by_count":28},{"id":"2008.10134","title":"m2caiSeg: Semantic Segmentation of Laparoscopic Images using Convolutional Neural Networks","created":"2020-08-23","cited_by_count":26},{"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":"1812.00033","title":"Learning from a tiny dataset of manual annotations: a teacher/student approach for surgical phase recognition","created":"2018-11-30","cited_by_count":21},{"id":"1806.05573","title":"Weakly-Supervised Learning for Tool Localization in Laparoscopic Videos","created":"2018-06-14","cited_by_count":20},{"id":"1906.11586","title":"CaDIS: Cataract Dataset for Image Segmentation","created":"2019-06-27","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":"2103.17120","title":"Learning Domain Adaptation with Model Calibration for Surgical Report Generation in Robotic Surgery","created":"2021-03-31","cited_by_count":16},{"id":"1604.04808","title":"Learning Models for Actions and Person-Object Interactions with Transfer to Question Answering","created":"2016-04-16","cited_by_count":15},{"id":"2102.13644","title":"Surgical Visual Domain Adaptation: Results from the MICCAI 2020 SurgVisDom Challenge","created":"2021-02-26","cited_by_count":14},{"id":"1603.09446","title":"Object Skeleton Extraction in Natural Images by Fusing Scale-associated Deep Side Outputs","created":"2016-03-31","cited_by_count":9},{"id":"2110.10965","title":"2020 CATARACTS Semantic Segmentation Challenge","created":"2021-10-21","cited_by_count":5},{"id":"2209.08647","title":"Why Deep Surgical Models Fail?: Revisiting Surgical Action Triplet Recognition through the Lens of Robustness","created":"2022-09-18","cited_by_count":4}],"next_cursor":null}