{"list":"other","total":88,"rows":[{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"2307.15189","title":"Med-Flamingo: a Multimodal Medical Few-shot Learner","created":"2023-07-27","cited_by_count":392},{"id":"1602.03012","title":"EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos","created":"2016-02-09","cited_by_count":367},{"id":"2102.09508","title":"Domain Adaptation for Medical Image Analysis: A Survey","created":"2021-02-18","cited_by_count":352},{"id":"1908.08796","title":"Reinforcement Learning in Healthcare: A Survey","created":"2019-08-22","cited_by_count":310},{"id":"2305.16986","title":"NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models","created":"2023-05-26","cited_by_count":280},{"id":"1804.08348","title":"Deep Facial Expression Recognition: A Survey","created":"2018-04-23","cited_by_count":270},{"id":"2407.06886","title":"Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI","created":"2024-07-09","cited_by_count":179},{"id":"2502.19634","title":"MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning","created":"2025-02-26","cited_by_count":173},{"id":"1902.06426","title":"2017 Robotic Instrument Segmentation Challenge","created":"2019-02-18","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":"2406.11161","title":"Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning","created":"2024-06-17","cited_by_count":121},{"id":"2001.09193","title":"VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images","created":"2020-01-24","cited_by_count":111},{"id":"2504.00993","title":"MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs","created":"2025-04-01","cited_by_count":110},{"id":"2407.12366","title":"NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models","created":"2024-07-17","cited_by_count":98},{"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":"2111.10056","title":"Medical Visual Question Answering: A Survey","created":"2021-11-19","cited_by_count":93},{"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":"2308.04758","title":"Bird's-Eye-View Scene Graph for Vision-Language Navigation","created":"2023-08-09","cited_by_count":72},{"id":"2403.14158","title":"Volumetric Environment Representation for Vision-Language Navigation","created":"2024-03-21","cited_by_count":63},{"id":"2003.09108","title":"FocalMix: Semi-Supervised Learning for 3D Medical Image Detection","created":"2020-03-20","cited_by_count":52},{"id":"1808.08180","title":"MVOR: A Multi-view RGB-D Operating Room Dataset for 2D and 3D Human Pose Estimation","created":"2018-08-24","cited_by_count":49},{"id":"2203.11937","title":"4D-OR: Semantic Scene Graphs for OR Domain Modeling","created":"2022-03-22","cited_by_count":49},{"id":"2304.09974","title":"SurgicalGPT: End-to-End Language-Vision GPT for Visual Question Answering in Surgery","created":"2023-04-19","cited_by_count":48},{"id":"2102.05281","title":"Biomedical Question Answering: A Survey of Approaches and Challenges","created":"2021-02-10","cited_by_count":46},{"id":"2105.14711","title":"CTSpine1K: A Large-Scale Dataset for Spinal Vertebrae Segmentation in Computed Tomography","created":"2021-05-31","cited_by_count":46},{"id":"2107.02823","title":"Deep Learning for Micro-expression Recognition: A Survey","created":"2021-07-06","cited_by_count":43},{"id":"2312.10251","title":"Advancing Surgical VQA with Scene Graph Knowledge","created":"2023-12-15","cited_by_count":41},{"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":"2407.12998","title":"Surgical Robot Transformer (SRT): Imitation Learning for Surgical Tasks","created":"2024-07-17","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":"2405.17835","title":"Deform3DGS: Flexible Deformation for Fast Surgical Scene Reconstruction with Gaussian Splatting","created":"2024-05-28","cited_by_count":38},{"id":"2412.14480","title":"GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answering","created":"2024-12-19","cited_by_count":37},{"id":"2408.07981","title":"LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning","created":"2024-08-15","cited_by_count":34},{"id":"2406.07471","title":"OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understanding","created":"2024-06-11","cited_by_count":32},{"id":"2108.13035","title":"SurRoL: An Open-source Reinforcement Learning Centered and dVRK Compatible Platform for Surgical Robot Learning","created":"2021-08-30","cited_by_count":31},{"id":"2506.02555","title":"SurgVLM: A Large Vision-Language Model and Systematic Evaluation Benchmark for Surgical Intelligence","created":"2025-06-03","cited_by_count":31},{"id":"2306.12217","title":"Lumbar spine segmentation in MR images: a dataset and a public benchmark","created":"2023-06-21","cited_by_count":30},{"id":"2310.11374","title":"DialogueLLM: Context and Emotion Knowledge-Tuned Large Language Models for Emotion Recognition in Conversations","created":"2023-10-17","cited_by_count":30},{"id":"2409.19590","title":"RoboNurse-VLA: Robotic Scrub Nurse System based on Vision-Language-Action Model","created":"2024-09-29","cited_by_count":29},{"id":"2103.13111","title":"MIcro-Surgical Anastomose Workflow recognition challenge report","created":"2021-03-24","cited_by_count":28},{"id":"2503.02579","title":"MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical Environments","created":"2025-03-04","cited_by_count":28},{"id":"2503.13415","title":"A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectives","created":"2025-03-17","cited_by_count":27},{"id":"2506.09513","title":"ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning","created":"2025-06-11","cited_by_count":27},{"id":"2008.10134","title":"m2caiSeg: Semantic Segmentation of Laparoscopic Images using Convolutional Neural Networks","created":"2020-08-23","cited_by_count":26},{"id":"2204.10129","title":"OSSO: Obtaining Skeletal Shape from Outside","created":"2022-04-21","cited_by_count":25},{"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":"2303.13293","title":"LABRAD-OR: Lightweight Memory Scene Graphs for Accurate Bimodal Reasoning in Dynamic Operating Rooms","created":"2023-03-23","cited_by_count":21},{"id":"2407.15087","title":"Navigation Instruction Generation with BEV Perception and Large Language Models","created":"2024-07-21","cited_by_count":21},{"id":"2112.08189","title":"ST-MTL: Spatio-Temporal Multitask Learning Model to Predict Scanpath While Tracking Instruments in Robotic Surgery","created":"2021-12-10","cited_by_count":20},{"id":"2410.14250","title":"Vision-Language Navigation with Energy-Based Policy","created":"2024-10-18","cited_by_count":19},{"id":"2312.07352","title":"CholecTrack20: A Multi-Perspective Tracking Dataset for Surgical Tools","created":"2023-12-12","cited_by_count":17},{"id":"2407.19305","title":"GP-VLS: A general-purpose vision language model for surgery","created":"2024-07-27","cited_by_count":17},{"id":"2404.16027","title":"ORBIT-Surgical: An Open-Simulation Framework for Learning Surgical Augmented Dexterity","created":"2024-04-24","cited_by_count":16},{"id":"2311.13793","title":"Evidential Active Recognition: Intelligent and Prudent Open-World Embodied Perception","created":"2023-11-23","cited_by_count":15},{"id":"2410.07540","title":"CoPESD: A Multi-Level Surgical Motion Dataset for Training Large Vision-Language Models to Co-Pilot Endoscopic Submucosal Dissection","created":"2024-10-10","cited_by_count":15},{"id":"2302.09606","title":"LapGym -- An Open Source Framework for Reinforcement Learning in Robot-Assisted Laparoscopic Surgery","created":"2023-02-19","cited_by_count":14},{"id":"2410.09292","title":"SurgicalGS: Dynamic 3D Gaussian Splatting for Accurate Robotic-Assisted Surgical Scene Reconstruction","created":"2024-10-11","cited_by_count":14},{"id":"2003.09487","title":"A Robotic 3D Perception System for Operating Room Environment Awareness","created":"2020-03-20","cited_by_count":13},{"id":"2011.06163","title":"Intermittent Visual Servoing: Efficiently Learning Policies Robust to Instrument Changes for High-precision Surgical Manipulation","created":"2020-11-12","cited_by_count":13},{"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":"2003.04949","title":"LC-GAN: Image-to-image Translation Based on Generative Adversarial Network for Endoscopic Images","created":"2020-03-10","cited_by_count":11},{"id":"2204.03195","title":"3D Perception based Imitation Learning under Limited Demonstration for Laparoscope Control in Robotic Surgery","created":"2022-04-07","cited_by_count":10},{"id":"2501.07468","title":"From Screens to Scenes: A Survey of Embodied AI in Healthcare","created":"2025-01-13","cited_by_count":10},{"id":"2505.07634","title":"Neural Brain: A Neuroscience-inspired Framework for Embodied Agents","created":"2025-05-12","cited_by_count":10},{"id":"2407.11906","title":"SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge","created":"2024-07-16","cited_by_count":8},{"id":"2001.10619","title":"Deep Learning in Multi-organ Segmentation","created":"2020-01-28","cited_by_count":7},{"id":"2406.12499","title":"Autonomous navigation of catheters and guidewires in mechanical thrombectomy using inverse reinforcement learning","created":"2024-06-18","cited_by_count":7},{"id":"2409.08750","title":"DexSim2Real$^{2}$: Building Explicit World Model for Precise Articulated Object Dexterous Manipulation","created":"2024-09-13","cited_by_count":7},{"id":"2508.08199","title":"Generalizable Operating Room Expert with Multimodal Enhancement","created":"2025-08-11","cited_by_count":7},{"id":"2208.03824","title":"Towards Graph Representation Learning Based Surgical Workflow Anticipation","created":"2022-08-07","cited_by_count":6},{"id":"2304.09632","title":"CASOG: Conservative Actor-critic with SmOoth Gradient for Skill Learning in Robot-Assisted Intervention","created":"2023-04-19","cited_by_count":6},{"id":"2310.04676","title":"Surgical Gym: A high-performance GPU-based platform for reinforcement learning with surgical robots","created":"2023-10-07","cited_by_count":6},{"id":"2312.00377","title":"SynFundus-1M: A High-quality Million-scale Synthetic fundus images Dataset with Fifteen Types of Annotation","created":"2023-12-01","cited_by_count":5},{"id":"2410.06420","title":"ERVQA: A Dataset to Benchmark the Readiness of Large Vision Language Models in Hospital Environments","created":"2024-10-08","cited_by_count":5},{"id":"2504.18969","title":"Advancing Face-to-Face Emotion Communication: A Multimodal Dataset (AFFEC)","created":"2025-04-26","cited_by_count":4},{"id":"2405.09375","title":"VascularPilot3D: Toward a 3D fully autonomous navigation for endovascular robotics","created":"2024-05-15","cited_by_count":3},{"id":"2504.14857","title":"SuFIA-BC: Generating High Quality Demonstration Data for Visuomotor Policy Learning in Surgical Subtasks","created":"2025-04-21","cited_by_count":3},{"id":"2507.01152","title":"SonoGym: High Performance Simulation for Challenging Surgical Tasks with Robotic Ultrasound","created":"2025-07-01","cited_by_count":3},{"id":"2202.11496","title":"MITI: SLAM Benchmark for Laparoscopic Surgery","created":"2022-02-23","cited_by_count":2},{"id":"2409.02724","title":"Surgical Task Automation Using Actor-Critic Frameworks and Self-Supervised Imitation Learning","created":"2024-09-04","cited_by_count":2},{"id":"2409.11688","title":"SLAM assisted 3D tracking system for laparoscopic surgery","created":"2024-09-18","cited_by_count":2},{"id":"2308.12156","title":"Multimodal Latent Emotion Recognition from Micro-expression and Physiological Signals","created":"2023-08-23","cited_by_count":1},{"id":"2311.17693","title":"Toward a Surgeon-in-the-Loop Ophthalmic Robotic Apprentice using Reinforcement and Imitation Learning","created":"2023-11-29","cited_by_count":1},{"id":"2409.02598","title":"SurgTrack: CAD-Free 3D Tracking of Real-world Surgical Instruments","created":"2024-09-04","cited_by_count":1}],"next_cursor":null}