{"list":"other","total":55,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"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":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"1612.03975","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","created":"2016-12-12","cited_by_count":1067},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"1906.00910","title":"Learning Representations by Maximizing Mutual Information Across Views","created":"2019-06-03","cited_by_count":734},{"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":"1710.05381","title":"A systematic study of the class imbalance problem in convolutional neural networks","created":"2017-10-15","cited_by_count":513},{"id":"1712.00377","title":"Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering","created":"2017-12-01","cited_by_count":339},{"id":"1904.03582","title":"Multi-Label Image Recognition with Graph Convolutional Networks","created":"2019-04-07","cited_by_count":322},{"id":"1606.00061","title":"Hierarchical Question-Image Co-Attention for Visual Question Answering","created":"2016-05-31","cited_by_count":278},{"id":"1812.07119","title":"Composing Text and Image for Image Retrieval - An Empirical Odyssey","created":"2018-12-18","cited_by_count":236},{"id":"2006.07529","title":"Rethinking the Value of Labels for Improving Class-Imbalanced Learning","created":"2020-06-13","cited_by_count":216},{"id":"1903.03326","title":"Knowledge-Embedded Routing Network for Scene Graph Generation","created":"2019-03-08","cited_by_count":164},{"id":"2001.03615","title":"In Defense of Grid Features for Visual Question Answering","created":"2020-01-10","cited_by_count":155},{"id":"1902.09720","title":"Learning a Deep ConvNet for Multi-label Classification with Partial Labels","created":"2019-02-26","cited_by_count":124},{"id":"1905.05908","title":"Task-Driven Modular Networks for Zero-Shot Compositional Learning","created":"2019-05-15","cited_by_count":121},{"id":"2008.01187","title":"PhraseCut: Language-based Image Segmentation in the Wild","created":"2020-08-03","cited_by_count":116},{"id":"1701.01619","title":"Learning From Noisy Large-Scale Datasets With Minimal Supervision","created":"2017-01-06","cited_by_count":115},{"id":"2101.00529","title":"VinVL: Revisiting Visual Representations in Vision-Language Models","created":"2021-01-02","cited_by_count":110},{"id":"2001.02314","title":"Bridging Knowledge Graphs to Generate Scene Graphs","created":"2020-01-07","cited_by_count":86},{"id":"1711.02816","title":"Multi-label Image Recognition by Recurrently Discovering Attentional Regions","created":"2017-11-08","cited_by_count":83},{"id":"2005.09241","title":"On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law","created":"2020-05-19","cited_by_count":74},{"id":"1307.5101","title":"Large-scale Multi-label Learning with Missing Labels","created":"2013-07-18","cited_by_count":58},{"id":"1610.01465","title":"Visual Question Answering: Datasets, Algorithms, and Future Challenges","created":"2016-10-05","cited_by_count":56},{"id":"1807.03903","title":"Deep Imbalanced Attribute Classification using Visual Attention Aggregation","created":"2018-07-10","cited_by_count":56},{"id":"1912.09021","title":"AANet: Attribute Attention Network for Person Re-Identifications","created":"2019-12-19","cited_by_count":56},{"id":"1312.4894","title":"Deep Convolutional Ranking for Multilabel Image Annotation","created":"2013-12-17","cited_by_count":47},{"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":"1704.03135","title":"Improving Pairwise Ranking for Multi-label Image Classification","created":"2017-04-11","cited_by_count":40},{"id":"1409.4327","title":"Zero Shot Recognition with Unreliable Attributes","created":"2014-09-15","cited_by_count":39},{"id":"2002.01464","title":"Visual Concept-Metaconcept Learning","created":"2020-02-04","cited_by_count":39},{"id":"1906.05750","title":"The iMaterialist Fashion Attribute Dataset","created":"2019-06-13","cited_by_count":37},{"id":"1601.03896","title":"Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures","created":"2016-01-15","cited_by_count":36},{"id":"1603.07054","title":"A Richly Annotated Dataset for Pedestrian Attribute Recognition","created":"2016-03-23","cited_by_count":33},{"id":"1904.05967","title":"TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning","created":"2019-04-11","cited_by_count":32},{"id":"1904.09317","title":"Challenges and Prospects in Vision and Language Research","created":"2019-04-19","cited_by_count":24},{"id":"1610.04787","title":"Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning","created":"2016-10-15","cited_by_count":20},{"id":"1803.09851","title":"Attributes as Operators: Factorizing Unseen Attribute-Object Compositions","created":"2018-03-27","cited_by_count":20},{"id":"1608.01441","title":"Improving Multi-label Learning with Missing Labels by Structured Semantic Correlations","created":"2016-08-04","cited_by_count":14},{"id":"1804.00117","title":"Multi-label Learning with Missing Labels using Mixed Dependency Graphs","created":"2018-03-31","cited_by_count":14},{"id":"1512.04103","title":"Deep Relative Attributes","created":"2015-12-13","cited_by_count":12},{"id":"1908.03335","title":"Recognizing Part Attributes with Insufficient Data","created":"2019-08-09","cited_by_count":12},{"id":"2007.06769","title":"Semi-supervised Learning with a Teacher-student Network for Generalized Attribute Prediction","created":"2020-07-14","cited_by_count":5},{"id":"1804.00112","title":"Compare and Contrast: Learning Prominent Visual Differences","created":"2018-03-31","cited_by_count":4}],"next_cursor":null}