{"list":"other","total":66,"rows":[{"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"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":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"1506.06724","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","created":"2015-06-22","cited_by_count":1043},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2012.07177","title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation","created":"2020-12-13","cited_by_count":596},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381},{"id":"1409.5185","title":"Deeply-Supervised Nets","created":"2014-09-18","cited_by_count":367},{"id":"1602.03012","title":"EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos","created":"2016-02-09","cited_by_count":367},{"id":"2102.11582","title":"Deep Deterministic Uncertainty: A Simple Baseline","created":"2021-02-23","cited_by_count":200},{"id":"2206.01653","title":"Metrics reloaded: Recommendations for image analysis validation","created":"2022-06-03","cited_by_count":195},{"id":"2212.07784","title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","created":"2022-12-14","cited_by_count":195},{"id":"1902.06426","title":"2017 Robotic Instrument Segmentation Challenge","created":"2019-02-18","cited_by_count":168},{"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":"2210.13452","title":"MetaFormer Baselines for Vision","created":"2022-10-24","cited_by_count":132},{"id":"2001.11190","title":"2018 Robotic Scene Segmentation Challenge","created":"2020-01-30","cited_by_count":124},{"id":"2403.09626","title":"Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding","created":"2024-03-14","cited_by_count":108},{"id":"2308.08746","title":"SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentation","created":"2023-08-17","cited_by_count":104},{"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":"2001.00570","title":"The Real-World-Weight Cross-Entropy Loss Function: Modeling the Costs of Mislabeling","created":"2020-01-03","cited_by_count":64},{"id":"2107.00649","title":"On the Practicality of Deterministic Epistemic Uncertainty","created":"2021-07-01","cited_by_count":62},{"id":"1910.05121","title":"Methods and open-source toolkit for analyzing and visualizing challenge results","created":"2019-10-11","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":"2202.05273","title":"Towards a Guideline for Evaluation Metrics in Medical Image Segmentation","created":"2022-02-10","cited_by_count":60},{"id":"2302.01790","title":"Understanding metric-related pitfalls in image analysis validation","created":"2023-02-03","cited_by_count":58},{"id":"1910.04071","title":"BIAS: Transparent reporting of biomedical image analysis challenges","created":"2019-10-09","cited_by_count":57},{"id":"2305.08989","title":"LoViT: Long Video Transformer for Surgical Phase Recognition","created":"2023-05-15","cited_by_count":56},{"id":"2401.00496","title":"SAR-RARP50: Segmentation of surgical instrumentation and Action Recognition on Robot-Assisted Radical Prostatectomy Challenge","created":"2023-12-31","cited_by_count":56},{"id":"2401.11174","title":"Pixel-Wise Recognition for Holistic Surgical Scene Understanding","created":"2024-01-20","cited_by_count":49},{"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":"2408.03867","title":"Surgformer: Surgical Transformer with Hierarchical Temporal Attention for Surgical Phase Recognition","created":"2024-08-07","cited_by_count":32},{"id":"2306.09244","title":"Text Promptable Surgical Instrument Segmentation with Vision-Language Models","created":"2023-06-15","cited_by_count":28},{"id":"2302.06294","title":"CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection","created":"2023-02-13","cited_by_count":23},{"id":"2202.06373","title":"Scheduling Techniques for Liver Segmentation: ReduceLRonPlateau Vs OneCycleLR","created":"2022-02-13","cited_by_count":19},{"id":"2304.13014","title":"Methods and datasets for segmentation of minimally invasive surgical instruments in endoscopic images and videos: A review of the state of the art","created":"2023-04-25","cited_by_count":18},{"id":"2406.16039","title":"CholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic Surgery","created":"2024-06-23","cited_by_count":16},{"id":"2410.07269","title":"Deep Learning for Surgical Instrument Recognition and Segmentation in Robotic-Assisted Surgeries: A Systematic Review","created":"2024-10-09","cited_by_count":13},{"id":"2107.02317","title":"Robotic Endoscope Control via Autonomous Instrument Tracking","created":"2021-07-05","cited_by_count":10},{"id":"2407.17361","title":"MuST: Multi-Scale Transformers for Surgical Phase Recognition","created":"2024-07-24","cited_by_count":8},{"id":"2407.17904","title":"Exploring the Effect of Dataset Diversity in Self-Supervised Learning for Surgical Computer Vision","created":"2024-07-25","cited_by_count":7},{"id":"2106.09302","title":"How can we learn (more) from challenges? A statistical approach to driving future algorithm development","created":"2021-06-17","cited_by_count":5}],"next_cursor":null}