{"list":"other","total":55,"rows":[{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2102.04306","title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","created":"2021-02-08","cited_by_count":1558},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"2404.08471","title":"Revisiting Feature Prediction for Learning Visual Representations from Video","created":"2024-02-15","cited_by_count":531},{"id":"2304.12620","title":"Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation","created":"2023-04-25","cited_by_count":490},{"id":"1602.03012","title":"EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos","created":"2016-02-09","cited_by_count":367},{"id":"2101.05224","title":"Big Self-Supervised Models Advance Medical Image Classification","created":"2021-01-13","cited_by_count":320},{"id":"2304.12306","title":"Segment Anything in Medical Images","created":"2023-04-24","cited_by_count":227},{"id":"2306.05422","title":"Tracking Everything Everywhere All at Once","created":"2023-06-08","cited_by_count":193},{"id":"2305.07027","title":"EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention","created":"2023-05-11","cited_by_count":172},{"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":"2012.12453","title":"CholecSeg8k: A Semantic Segmentation Dataset for Laparoscopic Cholecystectomy Based on Cholec80","created":"2020-12-23","cited_by_count":106},{"id":"2011.02284","title":"Surgical Data Science -- from Concepts toward Clinical Translation","created":"2020-10-30","cited_by_count":105},{"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":"1910.02241","title":"Self-supervised Feature Learning for 3D Medical Images by Playing a Rubik's Cube","created":"2019-10-05","cited_by_count":76},{"id":"2306.16741","title":"Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train","created":"2023-06-29","cited_by_count":75},{"id":"2112.08122","title":"Self-Supervised Monocular Depth and Ego-Motion Estimation in Endoscopy: Appearance Flow to the Rescue","created":"2021-12-15","cited_by_count":72},{"id":"1907.02757","title":"Self-Supervised Learning for Cardiac MR Image Segmentation by Anatomical Position Prediction","created":"2019-07-05","cited_by_count":70},{"id":"2007.07423","title":"Comparing to Learn: Surpassing ImageNet Pretraining on Radiographs By Comparing Image Representations","created":"2020-07-15","cited_by_count":69},{"id":"2307.15220","title":"Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures","created":"2023-07-27","cited_by_count":68},{"id":"2007.05405","title":"Recognition of Instrument-Tissue Interactions in Endoscopic Videos via Action Triplets","created":"2020-07-10","cited_by_count":66},{"id":"2010.05352","title":"MoCo-CXR: MoCo Pretraining Improves Representation and Transferability of Chest X-ray Models","created":"2020-10-11","cited_by_count":61},{"id":"1910.05121","title":"Methods and open-source toolkit for analyzing and visualizing challenge results","created":"2019-10-11","cited_by_count":60},{"id":"2207.00449","title":"Dissecting Self-Supervised Learning Methods for Surgical Computer Vision","created":"2022-07-01","cited_by_count":48},{"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":"2312.11250","title":"Challenges in Multi-centric Generalization: Phase and Step Recognition in Roux-en-Y Gastric Bypass Surgery","created":"2023-12-18","cited_by_count":40},{"id":"2410.00263","title":"Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation","created":"2024-09-30","cited_by_count":39},{"id":"2104.03178","title":"The SARAS Endoscopic Surgeon Action Detection (ESAD) dataset: Challenges and methods","created":"2021-04-07","cited_by_count":38},{"id":"2212.04155","title":"Latent Graph Representations for Critical View of Safety Assessment","created":"2022-12-08","cited_by_count":37},{"id":"2212.04582","title":"Towards Holistic Surgical Scene Understanding","created":"2022-12-08","cited_by_count":33},{"id":"2201.01283","title":"Self-supervised Learning from 100 Million Medical Images","created":"2022-01-04","cited_by_count":31},{"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":"2308.12394","title":"Self-Supervised Learning for Endoscopic Video Analysis","created":"2023-08-23","cited_by_count":22},{"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":"2306.11052","title":"A spatio-temporal network for video semantic segmentation in surgical videos","created":"2023-06-19","cited_by_count":17},{"id":"2109.07455","title":"Deep Bregman Divergence for Contrastive Learning of Visual Representations","created":"2021-09-15","cited_by_count":13},{"id":"2009.00681","title":"Aggregating Long-Term Context for Learning Laparoscopic and Robot-Assisted Surgical Workflows","created":"2020-09-01","cited_by_count":10},{"id":"2312.05968","title":"Jumpstarting Surgical Computer Vision","created":"2023-12-10","cited_by_count":8},{"id":"2110.12555","title":"hSDB-instrument: Instrument Localization Database for Laparoscopic and Robotic Surgeries","created":"2021-10-24","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":"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":"2412.03401","title":"Benchmarking Pretrained Attention-based Models for Real-Time Recognition in Robot-Assisted Esophagectomy","created":"2024-12-04","cited_by_count":2},{"id":"2412.04039","title":"Benchmarking and Enhancing Surgical Phase Recognition Models for Robotic-Assisted Esophagectomy","created":"2024-12-05","cited_by_count":2}],"next_cursor":null}