{"list":"other","total":100,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"1906.02530","title":"Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift","created":"2019-06-06","cited_by_count":1287},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1804.00015","title":"ESPnet: End-to-End Speech Processing Toolkit","created":"2018-03-30","cited_by_count":558},{"id":"1507.05717","title":"An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition","created":"2015-07-21","cited_by_count":520},{"id":"1701.06548","title":"Regularizing Neural Networks by Penalizing Confident Output Distributions","created":"2017-01-23","cited_by_count":464},{"id":"1904.01685","title":"Measuring Calibration in Deep Learning","created":"2019-04-02","cited_by_count":446},{"id":"1908.09822","title":"Confidence Regularized Self-Training","created":"2019-08-26","cited_by_count":419},{"id":"1604.06646","title":"Synthetic Data for Text Localisation in Natural Images","created":"2016-04-22","cited_by_count":396},{"id":"1709.05522","title":"AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline","created":"2017-09-16","cited_by_count":373},{"id":"1910.12656","title":"Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration","created":"2019-10-28","cited_by_count":364},{"id":"2002.09437","title":"Calibrating Deep Neural Networks using Focal Loss","created":"2020-02-21","cited_by_count":357},{"id":"1812.05720","title":"Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem","created":"2018-12-13","cited_by_count":323},{"id":"2003.07892","title":"Calibration of Pre-trained Transformers","created":"2020-03-17","cited_by_count":315},{"id":"1909.10155","title":"Verified Uncertainty Calibration","created":"2019-09-23","cited_by_count":309},{"id":"1905.11001","title":"On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks","created":"2019-05-27","cited_by_count":305},{"id":"2101.06329","title":"In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning","created":"2021-01-15","cited_by_count":301},{"id":"1406.2227","title":"Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition","created":"2014-06-09","cited_by_count":214},{"id":"2103.06495","title":"Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition","created":"2021-03-11","cited_by_count":194},{"id":"1904.01906","title":"What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis","created":"2019-04-03","cited_by_count":191},{"id":"2003.07329","title":"Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning","created":"2020-03-16","cited_by_count":190},{"id":"2102.09559","title":"CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning","created":"2021-02-18","cited_by_count":175},{"id":"2105.03889","title":"Conformer: Local Features Coupling Global Representations for Visual Recognition","created":"2021-05-09","cited_by_count":164},{"id":"1911.13273","title":"Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentation","created":"2019-11-29","cited_by_count":163},{"id":"1508.04395","title":"End-to-End Attention-based Large Vocabulary Speech Recognition","created":"2015-08-18","cited_by_count":151},{"id":"1909.07145","title":"ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)","created":"2019-09-16","cited_by_count":147},{"id":"2003.12294","title":"Towards Accurate Scene Text Recognition with Semantic Reasoning Networks","created":"2020-03-27","cited_by_count":131},{"id":"1811.00751","title":"Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition","created":"2018-11-02","cited_by_count":130},{"id":"1912.09641","title":"ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard","created":"2019-12-20","cited_by_count":128},{"id":"1803.00047","title":"Analyzing Uncertainty in Neural Machine Translation","created":"2018-02-28","cited_by_count":126},{"id":"2012.07923","title":"Improving model calibration with accuracy versus uncertainty optimization","created":"2020-12-14","cited_by_count":123},{"id":"1909.07741","title":"ICDAR 2019 Competition on Large-scale Street View Text with Partial Labeling -- RRC-LSVT","created":"2019-09-17","cited_by_count":122},{"id":"2005.10977","title":"SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition","created":"2020-05-22","cited_by_count":119},{"id":"2007.01458","title":"Confidence-Aware Learning for Deep Neural Networks","created":"2020-07-03","cited_by_count":113},{"id":"1708.09585","title":"ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17)","created":"2017-08-31","cited_by_count":105},{"id":"2012.08668","title":"Mitigating Bias in Calibration Error Estimation","created":"2020-12-15","cited_by_count":101},{"id":"1612.02695","title":"Towards better decoding and language model integration in sequence to sequence models","created":"2016-12-08","cited_by_count":100},{"id":"2107.10161","title":"Evidential Deep Learning for Open Set Action Recognition","created":"2021-07-21","cited_by_count":96},{"id":"2008.05105","title":"Local Temperature Scaling for Probability Calibration","created":"2020-08-12","cited_by_count":95},{"id":"2008.00334","title":"Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning","created":"2020-08-01","cited_by_count":91},{"id":"2111.15430","title":"The Devil is in the Margin: Margin-based Label Smoothing for Network Calibration","created":"2021-11-30","cited_by_count":91},{"id":"1508.05154","title":"Posterior calibration and exploratory analysis for natural language processing models","created":"2015-08-21","cited_by_count":76},{"id":"2003.11288","title":"SCATTER: Selective Context Attentional Scene Text Recognizer","created":"2020-03-25","cited_by_count":69},{"id":"2009.09450","title":"Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition","created":"2020-09-20","cited_by_count":69},{"id":"1903.00802","title":"Calibration of Encoder Decoder Models for Neural Machine Translation","created":"2019-03-03","cited_by_count":68},{"id":"1805.02641","title":"Label Refinery: Improving ImageNet Classification through Label Progression","created":"2018-05-07","cited_by_count":65},{"id":"1910.02562","title":"MASTER: Multi-Aspect Non-local Network for Scene Text Recognition","created":"2019-10-07","cited_by_count":65},{"id":"2005.00963","title":"On the Inference Calibration of Neural Machine Translation","created":"2020-05-03","cited_by_count":61},{"id":"1801.01315","title":"PixelLink: Detecting Scene Text via Instance Segmentation","created":"2018-01-04","cited_by_count":60},{"id":"1906.04933","title":"Non-Parametric Calibration for Classification","created":"2019-06-12","cited_by_count":57},{"id":"2112.15093","title":"Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study","created":"2021-12-30","cited_by_count":53},{"id":"2203.13834","title":"A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration","created":"2022-03-25","cited_by_count":49},{"id":"2102.12182","title":"Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration","created":"2021-02-24","cited_by_count":48},{"id":"2008.00923","title":"Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning","created":"2020-08-03","cited_by_count":46},{"id":"2005.03959","title":"On Vocabulary Reliance in Scene Text Recognition","created":"2020-05-08","cited_by_count":39},{"id":"2012.05481","title":"Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition","created":"2020-12-10","cited_by_count":39},{"id":"2010.11428","title":"Confidence Estimation for Attention-based Sequence-to-sequence Models for Speech Recognition","created":"2020-10-22","cited_by_count":35},{"id":"2303.14736","title":"Disentangling Writer and Character Styles for Handwriting Generation","created":"2023-03-26","cited_by_count":35},{"id":"1909.00157","title":"Improving Back-Translation with Uncertainty-based Confidence Estimation","created":"2019-08-31","cited_by_count":34},{"id":"2012.06508","title":"Confidence Estimation via Auxiliary Models","created":"2020-12-11","cited_by_count":34},{"id":"1909.12358","title":"Can We Trust You? On Calibration of a Probabilistic Object Detector for Autonomous Driving","created":"2019-09-26","cited_by_count":30},{"id":"1902.09191","title":"Improving Neural Response Diversity with Frequency-Aware Cross-Entropy Loss","created":"2019-02-25","cited_by_count":29},{"id":"2006.13092","title":"Multi-Class Uncertainty Calibration via Mutual Information Maximization-based Binning","created":"2020-06-23","cited_by_count":27},{"id":"1809.10877","title":"Learning for Single-Shot Confidence Calibration in Deep Neural Networks through Stochastic Inferences","created":"2018-09-28","cited_by_count":25},{"id":"1908.11528","title":"Bin-wise Temperature Scaling (BTS): Improvement in Confidence Calibration Performance through Simple Scaling Techniques","created":"2019-08-30","cited_by_count":23},{"id":"1912.01730","title":"Distance-Based Learning from Errors for Confidence Calibration","created":"2019-12-03","cited_by_count":23},{"id":"1810.11586","title":"Attended Temperature Scaling: A Practical Approach for Calibrating Deep Neural Networks","created":"2018-10-27","cited_by_count":21},{"id":"1912.10000","title":"Probability Calibration for Knowledge Graph Embedding Models","created":"2019-12-20","cited_by_count":21},{"id":"1906.09551","title":"Confidence Calibration for Convolutional Neural Networks Using Structured Dropout","created":"2019-06-23","cited_by_count":19},{"id":"2303.07012","title":"AGTGAN: Unpaired Image Translation for Photographic Ancient Character Generation","created":"2023-03-13","cited_by_count":17},{"id":"1803.05566","title":"Advancing Acoustic-to-Word CTC Model","created":"2018-03-15","cited_by_count":15},{"id":"2002.05033","title":"Active Learning for Sound Event Detection","created":"2020-02-12","cited_by_count":14},{"id":"2104.09286","title":"Learning to Cascade: Confidence Calibration for Improving the Accuracy and Computational Cost of Cascade Inference Systems","created":"2021-04-15","cited_by_count":14},{"id":"2010.07447","title":"Semantic Label Smoothing for Sequence to Sequence Problems","created":"2020-10-15","cited_by_count":13},{"id":"2012.12643","title":"On Calibration of Scene-Text Recognition Models","created":"2020-12-23","cited_by_count":9},{"id":"2101.02971","title":"From Black-box to White-box: Examining Confidence Calibration under different Conditions","created":"2021-01-08","cited_by_count":8},{"id":"1903.11701","title":"Zero-shot Image Recognition Using Relational Matching, Adaptation and Calibration","created":"2019-03-27","cited_by_count":7},{"id":"2007.01659","title":"Diagnostic Uncertainty Calibration: Towards Reliable Machine Predictions in Medical Domain","created":"2020-07-03","cited_by_count":7},{"id":"2108.13630","title":"SimulLR: Simultaneous Lip Reading Transducer with Attention-Guided Adaptive Memory","created":"2021-08-31","cited_by_count":7},{"id":"1805.05062","title":"Token-level and sequence-level loss smoothing for RNN language models","created":"2018-05-14","cited_by_count":6},{"id":"2002.02644","title":"Temporal Probability Calibration","created":"2020-02-07","cited_by_count":5},{"id":"2303.06946","title":"Context-Aware Selective Label Smoothing for Calibrating Sequence Recognition Model","created":"2023-03-13","cited_by_count":5},{"id":"2010.13856","title":"Data Troubles in Sentence Level Confidence Estimation for Machine Translation","created":"2020-10-26","cited_by_count":3},{"id":"2004.03437","title":"Homophone-based Label Smoothing in End-to-End Automatic Speech Recognition","created":"2020-04-07","cited_by_count":2},{"id":"1910.14175","title":"Learn-By-Calibrating: Using Calibration as a Training Objective","created":"2019-10-30","cited_by_count":1}],"next_cursor":null}