{"list":"other","total":63,"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":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1703.06103","title":"Modeling Relational Data with Graph Convolutional Networks","created":"2017-03-17","cited_by_count":1694},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"2004.05498","title":"FDA: Fourier Domain Adaptation for Semantic Segmentation","created":"2020-04-11","cited_by_count":541},{"id":"1611.05267","title":"Temporal Convolutional Networks for Action Segmentation and Detection","created":"2016-11-16","cited_by_count":508},{"id":"1701.06548","title":"Regularizing Neural Networks by Penalizing Confident Output Distributions","created":"2017-01-23","cited_by_count":464},{"id":"1602.03012","title":"EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos","created":"2016-02-09","cited_by_count":367},{"id":"2105.11120","title":"A Fourier-based Framework for Domain Generalization","created":"2021-05-24","cited_by_count":290},{"id":"1805.07932","title":"Bilinear Attention Networks","created":"2018-05-21","cited_by_count":280},{"id":"1608.08242","title":"Temporal Convolutional Networks: A Unified Approach to Action Segmentation","created":"2016-08-29","cited_by_count":199},{"id":"2003.10751","title":"TeCNO: Surgical Phase Recognition with Multi-Stage Temporal Convolutional Networks","created":"2020-03-24","cited_by_count":141},{"id":"1604.04004","title":"Understanding How Image Quality Affects Deep Neural Networks","created":"2016-04-14","cited_by_count":119},{"id":"2009.14082","title":"Attentional Feature Fusion","created":"2020-09-29","cited_by_count":115},{"id":"2106.05786","title":"CAT: Cross Attention in Vision Transformer","created":"2021-06-10","cited_by_count":92},{"id":"2109.14285","title":"Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration","created":"2021-09-29","cited_by_count":92},{"id":"1602.02995","title":"Segmental Spatiotemporal CNNs for Fine-grained Action Segmentation","created":"2016-02-09","cited_by_count":78},{"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":"2404.15993","title":"Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach","created":"2024-04-24","cited_by_count":76},{"id":"2308.01222","title":"Calibration in Deep Learning: A Survey of the State-of-the-Art","created":"2023-08-02","cited_by_count":75},{"id":"2307.15220","title":"Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures","created":"2023-07-27","cited_by_count":68},{"id":"2103.16327","title":"Temporal Memory Relation Network for Workflow Recognition from Surgical Video","created":"2021-03-30","cited_by_count":66},{"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":"2401.06013","title":"Surgical-DINO: Adapter Learning of Foundation Models for Depth Estimation in Endoscopic Surgery","created":"2024-01-11","cited_by_count":52},{"id":"2401.11174","title":"Pixel-Wise Recognition for Holistic Surgical Scene Understanding","created":"2024-01-20","cited_by_count":49},{"id":"1911.07848","title":"Modality to Modality Translation: An Adversarial Representation Learning and Graph Fusion Network for Multimodal Fusion","created":"2019-11-18","cited_by_count":45},{"id":"2305.11692","title":"Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery","created":"2023-05-19","cited_by_count":44},{"id":"2405.10075","title":"HecVL: Hierarchical Video-Language Pretraining for Zero-shot Surgical Phase Recognition","created":"2024-05-16","cited_by_count":42},{"id":"2210.06391","title":"What Makes Graph Neural Networks Miscalibrated?","created":"2022-10-12","cited_by_count":40},{"id":"1704.02798","title":"Bayesian Recurrent Neural Networks","created":"2017-04-10","cited_by_count":39},{"id":"2405.10948","title":"Surgical-LVLM: Learning to Adapt Large Vision-Language Model for Grounded Visual Question Answering in Robotic Surgery","created":"2024-03-22","cited_by_count":39},{"id":"2408.03867","title":"Surgformer: Surgical Transformer with Hierarchical Temporal Attention for Surgical Phase Recognition","created":"2024-08-07","cited_by_count":32},{"id":"2409.17407","title":"Post-hoc Reward Calibration: A Case Study on Length Bias","created":"2024-09-25","cited_by_count":29},{"id":"2103.13111","title":"MIcro-Surgical Anastomose Workflow recognition challenge report","created":"2021-03-24","cited_by_count":28},{"id":"2112.13776","title":"Transformer Uncertainty Estimation with Hierarchical Stochastic Attention","created":"2021-12-27","cited_by_count":21},{"id":"2109.05263","title":"Class-Distribution-Aware Calibration for Long-Tailed Visual Recognition","created":"2021-09-11","cited_by_count":19},{"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":"2311.12436","title":"Classifier Calibration with ROC-Regularized Isotonic Regression","created":"2023-11-21","cited_by_count":19},{"id":"2407.16714","title":"Masked Graph Learning with Recurrent Alignment for Multimodal Emotion Recognition in Conversation","created":"2024-07-23","cited_by_count":19},{"id":"2011.01619","title":"Relational Graph Learning on Visual and Kinematics Embeddings for Accurate Gesture Recognition in Robotic Surgery","created":"2020-11-03","cited_by_count":17},{"id":"2307.05182","title":"CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery","created":"2023-07-11","cited_by_count":17},{"id":"1806.08089","title":"Deep Reinforcement Learning for Surgical Gesture Segmentation and Classification","created":"2018-06-21","cited_by_count":15},{"id":"2307.02452","title":"LLCaps: Learning to Illuminate Low-Light Capsule Endoscopy with Curved Wavelet Attention and Reverse Diffusion","created":"2023-07-05","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":"2412.14018","title":"SurgSora: Object-Aware Diffusion Model for Controllable Surgical Video Generation","created":"2024-12-18","cited_by_count":15},{"id":"1905.02296","title":"Are Graph Neural Networks Miscalibrated?","created":"2019-05-07","cited_by_count":14},{"id":"2002.02921","title":"Temporal Segmentation of Surgical Sub-tasks through Deep Learning with Multiple Data Sources","created":"2020-02-07","cited_by_count":12},{"id":"2405.10550","title":"LighTDiff: Surgical Endoscopic Image Low-Light Enhancement with T-Diffusion","created":"2024-05-17","cited_by_count":12},{"id":"2101.08316","title":"Ensemble manifold based regularized multi-modal graph convolutional network for cognitive ability prediction","created":"2021-01-20","cited_by_count":9},{"id":"2312.06645","title":"Beyond Classification: Definition and Density-based Estimation of Calibration in Object Detection","created":"2023-12-11","cited_by_count":9},{"id":"2410.20314","title":"Wavelet-based Mamba with Fourier Adjustment for Low-light Image Enhancement","created":"2024-10-27","cited_by_count":8},{"id":"2402.06985","title":"OSSAR: Towards Open-Set Surgical Activity Recognition in Robot-assisted Surgery","created":"2024-02-10","cited_by_count":7},{"id":"2407.12330","title":"Uncertainty Calibration with Energy Based Instance-wise Scaling in the Wild Dataset","created":"2024-07-17","cited_by_count":4},{"id":"2309.00957","title":"Visual-Kinematics Graph Learning for Procedure-agnostic Instrument Tip Segmentation in Robotic Surgeries","created":"2023-09-02","cited_by_count":1},{"id":"2410.03999","title":"Impact of Regularization on Calibration and Robustness: from the Representation Space Perspective","created":"2024-10-05","cited_by_count":1}],"next_cursor":null}