{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"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":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"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":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"2003.00196","title":"First Order Motion Model for Image Animation","created":"2020-02-29","cited_by_count":704},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"id":"2104.14548","title":"With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations","created":"2021-04-29","cited_by_count":326},{"id":"1609.08675","title":"YouTube-8M: A Large-Scale Video Classification Benchmark","created":"2016-09-27","cited_by_count":324},{"id":"2204.07141","title":"Masked Siamese Networks for Label-Efficient Learning","created":"2022-04-14","cited_by_count":302},{"id":"2111.10337","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","created":"2021-11-19","cited_by_count":226},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"1804.03619","title":"Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation","created":"2018-04-10","cited_by_count":162},{"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":"2202.02794","title":"Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets","created":"2022-02-06","cited_by_count":133},{"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":"1907.06099","title":"Multi-Task Recurrent Convolutional Network with Correlation Loss for Surgical Video Analysis","created":"2019-07-13","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":"2103.16327","title":"Temporal Memory Relation Network for Workflow Recognition from Surgical Video","created":"2021-03-30","cited_by_count":66},{"id":"2206.11053","title":"Surgical-VQA: Visual Question Answering in Surgical Scenes using Transformer","created":"2022-06-22","cited_by_count":59},{"id":"2305.08989","title":"LoViT: Long Video Transformer for Surgical Phase Recognition","created":"2023-05-15","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":"2207.00449","title":"Dissecting Self-Supervised Learning Methods for Surgical Computer Vision","created":"2022-07-01","cited_by_count":48},{"id":"2405.10075","title":"HecVL: Hierarchical Video-Language Pretraining for Zero-shot Surgical Phase Recognition","created":"2024-05-16","cited_by_count":42},{"id":"2312.10251","title":"Advancing Surgical VQA with Scene Graph Knowledge","created":"2023-12-15","cited_by_count":41},{"id":"1610.09278","title":"The TUM LapChole dataset for the M2CAI 2016 workflow challenge","created":"2016-10-28","cited_by_count":38},{"id":"2104.10824","title":"Colonoscopy Polyp Detection and Classification: Dataset Creation and Comparative Evaluations","created":"2021-04-22","cited_by_count":38},{"id":"2408.07981","title":"LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning","created":"2024-08-15","cited_by_count":34},{"id":"2311.15206","title":"Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding","created":"2023-11-26","cited_by_count":29},{"id":"2403.05949","title":"General surgery vision transformer: A video pre-trained foundation model for general surgery","created":"2024-03-09","cited_by_count":25},{"id":"2501.09436","title":"Scaling up self-supervised learning for improved surgical foundation models","created":"2025-01-16","cited_by_count":25},{"id":"2308.12394","title":"Self-Supervised Learning for Endoscopic Video Analysis","created":"2023-08-23","cited_by_count":22},{"id":"2405.19644","title":"EgoSurgery-Phase: A Dataset of Surgical Phase Recognition from Egocentric Open Surgery Videos","created":"2024-05-30","cited_by_count":20},{"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":"2111.04911","title":"Real-time Instance Segmentation of Surgical Instruments using Attention and Multi-scale Feature Fusion","created":"2021-11-09","cited_by_count":17},{"id":"2306.11052","title":"A spatio-temporal network for video semantic segmentation in surgical videos","created":"2023-06-19","cited_by_count":17},{"id":"2403.08848","title":"FocusMAE: Gallbladder Cancer Detection from Ultrasound Videos with Focused Masked Autoencoders","created":"2024-03-13","cited_by_count":8},{"id":"2012.12844","title":"Automating Surgical Peg Transfer: Calibration with Deep Learning Can Exceed Speed, Accuracy, and Consistency of Humans","created":"2020-12-23","cited_by_count":7},{"id":"2305.11451","title":"SurgMAE: Masked Autoencoders for Long Surgical Video Analysis","created":"2023-05-19","cited_by_count":7},{"id":"2303.10173","title":"VideoSum: A Python Library for Surgical Video Summarization","created":"2023-02-15","cited_by_count":4},{"id":"2410.17642","title":"Surgical Scene Segmentation by Transformer With Asymmetric Feature Enhancement","created":"2024-10-23","cited_by_count":2}],"next_cursor":null}