{"list":"other","total":58,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"1607.04606","title":"Enriching Word Vectors with Subword Information","created":"2016-07-15","cited_by_count":1583},{"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":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1803.01534","title":"Path Aggregation Network for Instance Segmentation","created":"2018-03-05","cited_by_count":798},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"1707.00600","title":"Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly","created":"2017-07-03","cited_by_count":538},{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446},{"id":"1608.00187","title":"Visual Relationship Detection with Language Priors","created":"2016-07-31","cited_by_count":334},{"id":"1810.12890","title":"DropBlock: A regularization method for convolutional networks","created":"2018-10-30","cited_by_count":262},{"id":"2009.12991","title":"Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect","created":"2020-09-28","cited_by_count":256},{"id":"1904.08739","title":"Cascaded Partial Decoder for Fast and Accurate Salient Object Detection","created":"2019-04-18","cited_by_count":216},{"id":"2104.00466","title":"Improving Calibration for Long-Tailed Recognition","created":"2021-04-01","cited_by_count":212},{"id":"1812.01784","title":"Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders","created":"2018-12-05","cited_by_count":206},{"id":"1801.05401","title":"Low-Shot Learning from Imaginary Data","created":"2018-01-16","cited_by_count":181},{"id":"1605.04253","title":"An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild","created":"2016-05-13","cited_by_count":146},{"id":"2007.03943","title":"Remix: Rebalanced Mixup","created":"2020-07-08","cited_by_count":144},{"id":"2007.12407","title":"Visual Compositional Learning for Human-Object Interaction Detection","created":"2020-07-24","cited_by_count":130},{"id":"1905.05908","title":"Task-Driven Modular Networks for Zero-Shot Compositional Learning","created":"2019-05-15","cited_by_count":121},{"id":"1512.05830","title":"Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks","created":"2015-12-18","cited_by_count":115},{"id":"2102.01987","title":"Learning Graph Embeddings for Compositional Zero-shot Learning","created":"2021-02-03","cited_by_count":112},{"id":"2101.12609","title":"Open World Compositional Zero-Shot Learning","created":"2021-01-29","cited_by_count":101},{"id":"2112.00412","title":"The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification","created":"2021-12-01","cited_by_count":100},{"id":"2106.09707","title":"Learning to Predict Visual Attributes in the Wild","created":"2021-06-17","cited_by_count":96},{"id":"2004.00587","title":"Symmetry and Group in Attribute-Object Compositions","created":"2020-04-01","cited_by_count":89},{"id":"1711.00941","title":"Deep Active Learning over the Long Tail","created":"2017-11-02","cited_by_count":84},{"id":"2103.10619","title":"Scalable Vision Transformers with Hierarchical Pooling","created":"2021-03-19","cited_by_count":84},{"id":"2006.14610","title":"A causal view of compositional zero-shot recognition","created":"2020-06-25","cited_by_count":78},{"id":"2003.13261","title":"Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learning","created":"2020-03-30","cited_by_count":71},{"id":"2106.09859","title":"RSG: A Simple but Effective Module for Learning Imbalanced Datasets","created":"2021-06-18","cited_by_count":61},{"id":"1807.03903","title":"Deep Imbalanced Attribute Classification using Visual Attention Aggregation","created":"2018-07-10","cited_by_count":56},{"id":"2205.08536","title":"Disentangling Visual Embeddings for Attributes and Objects","created":"2022-05-17","cited_by_count":55},{"id":"2206.14475","title":"Siamese Contrastive Embedding Network for Compositional Zero-Shot Learning","created":"2022-06-29","cited_by_count":55},{"id":"1412.6568","title":"Improving zero-shot learning by mitigating the hubness problem","created":"2014-12-20","cited_by_count":54},{"id":"1910.04562","title":"Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization","created":"2019-10-10","cited_by_count":46},{"id":"2106.00305","title":"Independent Prototype Propagation for Zero-Shot Compositionality","created":"2021-06-01","cited_by_count":42},{"id":"2205.06784","title":"KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning","created":"2022-05-13","cited_by_count":41},{"id":"2108.00873","title":"Shallow Feature Matters for Weakly Supervised Object Localization","created":"2021-08-02","cited_by_count":34},{"id":"1904.05967","title":"TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning","created":"2019-04-11","cited_by_count":32},{"id":"2110.05741","title":"Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localization","created":"2021-10-12","cited_by_count":30},{"id":"2206.00415","title":"Learning Invariant Visual Representations for Compositional Zero-Shot Learning","created":"2022-06-01","cited_by_count":24},{"id":"2210.11557","title":"Learning Attention Propagation for Compositional Zero-Shot Learning","created":"2022-10-20","cited_by_count":20},{"id":"2108.04603","title":"Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognition","created":"2021-08-10","cited_by_count":19},{"id":"1911.11612","title":"On Symbiosis of Attribute Prediction and Semantic Segmentation","created":"2019-11-23","cited_by_count":6}],"next_cursor":null}