{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1710.11063","title":"Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks","created":"2017-10-30","cited_by_count":939},{"id":"1806.07421","title":"RISE: Randomized Input Sampling for Explanation of Black-box Models","created":"2018-06-19","cited_by_count":838},{"id":"1704.03296","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","created":"2017-04-11","cited_by_count":612},{"id":"1708.03985","title":"AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild","created":"2017-08-14","cited_by_count":492},{"id":"1608.00507","title":"Top-down Neural Attention by Excitation Backprop","created":"2016-08-01","cited_by_count":321},{"id":"1804.08348","title":"Deep Facial Expression Recognition: A Survey","created":"2018-04-23","cited_by_count":270},{"id":"1910.08485","title":"Understanding Deep Networks via Extremal Perturbations and Smooth Masks","created":"2019-10-18","cited_by_count":259},{"id":"1705.07857","title":"Real Time Image Saliency for Black Box Classifiers","created":"2017-05-22","cited_by_count":246},{"id":"1804.06962","title":"Adversarial Complementary Learning for Weakly Supervised Object Localization","created":"2018-04-19","cited_by_count":166},{"id":"1902.10421","title":"FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference","created":"2019-02-27","cited_by_count":162},{"id":"2008.02312","title":"Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs","created":"2020-08-05","cited_by_count":151},{"id":"1905.04075","title":"Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition","created":"2019-05-10","cited_by_count":127},{"id":"1908.10028","title":"Attention-based Dropout Layer for Weakly Supervised Object Localization","created":"2019-08-27","cited_by_count":125},{"id":"2001.07437","title":"Evaluating Weakly Supervised Object Localization Methods Right","created":"2020-01-21","cited_by_count":105},{"id":"2108.11116","title":"TransFER: Learning Relation-aware Facial Expression Representations with Transformers","created":"2021-08-25","cited_by_count":85},{"id":"2205.01782","title":"Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition","created":"2022-05-02","cited_by_count":82},{"id":"1804.00880","title":"Weakly Supervised Instance Segmentation using Class Peak Response","created":"2018-04-03","cited_by_count":75},{"id":"2008.05096","title":"Inter-Image Communication for Weakly Supervised Localization","created":"2020-08-12","cited_by_count":52},{"id":"2204.04083","title":"POSTER: A Pyramid Cross-Fusion Transformer Network for Facial Expression Recognition","created":"2022-04-08","cited_by_count":49},{"id":"2212.05463","title":"Vision Transformer with Attentive Pooling for Robust Facial Expression Recognition","created":"2022-12-11","cited_by_count":35},{"id":"2108.00873","title":"Shallow Feature Matters for Weakly Supervised Object Localization","created":"2021-08-02","cited_by_count":34},{"id":"2109.08409","title":"Expression Snippet Transformer for Robust Video-based Facial Expression Recognition","created":"2021-09-17","cited_by_count":33},{"id":"2010.03023","title":"IS-CAM: Integrated Score-CAM for axiomatic-based explanations","created":"2020-10-06","cited_by_count":29},{"id":"1909.03354","title":"Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey","created":"2019-09-08","cited_by_count":28},{"id":"2110.09772","title":"Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry","created":"2021-10-19","cited_by_count":27},{"id":"2011.07221","title":"Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images via Max-Min Uncertainty","created":"2020-11-14","cited_by_count":26},{"id":"2109.07069","title":"F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling","created":"2021-09-15","cited_by_count":26},{"id":"2301.12149","title":"POSTER++: A simpler and stronger facial expression recognition network","created":"2023-01-28","cited_by_count":25},{"id":"2004.09681","title":"Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph Convolution","created":"2020-04-20","cited_by_count":22},{"id":"2211.01412","title":"CAMANet: Class Activation Map Guided Attention Network for Radiology Report Generation","created":"2022-11-02","cited_by_count":22},{"id":"1709.01829","title":"Soft Proposal Networks for Weakly Supervised Object Localization","created":"2017-09-06","cited_by_count":21},{"id":"1505.04026","title":"Automatic Facial Expression Recognition Using Features of Salient Facial Patches","created":"2015-05-15","cited_by_count":13},{"id":"2010.13386","title":"Video-based Facial Expression Recognition using Graph Convolutional Networks","created":"2020-10-26","cited_by_count":13},{"id":"2209.09209","title":"Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization","created":"2022-09-09","cited_by_count":13},{"id":"2208.14542","title":"TCAM: Temporal Class Activation Maps for Object Localization in Weakly-Labeled Unconstrained Videos","created":"2022-08-30","cited_by_count":12},{"id":"1805.03487","title":"Joint Action Unit localisation and intensity estimation through heatmap regression","created":"2018-05-09","cited_by_count":10},{"id":"2101.00317","title":"Identity-aware Facial Expression Recognition in Compressed Video","created":"2021-01-01","cited_by_count":9},{"id":"2201.02445","title":"Negative Evidence Matters in Interpretable Histology Image Classification","created":"2022-01-07","cited_by_count":8},{"id":"2310.06196","title":"DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object Localization","created":"2023-10-09","cited_by_count":8},{"id":"2303.09044","title":"CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos","created":"2023-03-16","cited_by_count":7},{"id":"2303.10438","title":"Spatial-Aware Token for Weakly Supervised Object Localization","created":"2023-03-18","cited_by_count":7},{"id":"1912.01522","title":"Convolutional STN for Weakly Supervised Object Localization","created":"2019-12-03","cited_by_count":6},{"id":"2209.09195","title":"Constrained Sampling for Class-Agnostic Weakly Supervised Object Localization","created":"2022-09-09","cited_by_count":6},{"id":"2203.12905","title":"Privileged Attribution Constrained Deep Networks for Facial Expression Recognition","created":"2022-03-24","cited_by_count":4}],"next_cursor":null}