{"list":"other","total":52,"rows":[{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"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":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"id":"1603.08511","title":"Colorful Image Colorization","created":"2016-03-28","cited_by_count":1114},{"id":"1505.05192","title":"Unsupervised Visual Representation Learning by Context Prediction","created":"2015-05-19","cited_by_count":1066},{"id":"1904.04232","title":"A Closer Look at Few-shot Classification","created":"2019-04-08","cited_by_count":684},{"id":"1811.10830","title":"From Recognition to Cognition: Visual Commonsense Reasoning","created":"2018-11-27","cited_by_count":556},{"id":"2006.06882","title":"Rethinking Pre-training and Self-training","created":"2020-06-11","cited_by_count":352},{"id":"1506.06726","title":"Skip-Thought Vectors","created":"2015-06-22","cited_by_count":322},{"id":"1511.03416","title":"Visual7W: Grounded Question Answering in Images","created":"2015-11-11","cited_by_count":318},{"id":"1810.09502","title":"How to train your MAML","created":"2018-10-22","cited_by_count":309},{"id":"1812.02391","title":"Meta-Transfer Learning for Few-Shot Learning","created":"2018-12-06","cited_by_count":306},{"id":"1906.10169","title":"RUBi: Reducing Unimodal Biases in Visual Question Answering","created":"2019-06-24","cited_by_count":185},{"id":"1801.05401","title":"Low-Shot Learning from Imaginary Data","created":"2018-01-16","cited_by_count":181},{"id":"2001.03615","title":"In Defense of Grid Features for Visual Question Answering","created":"2020-01-10","cited_by_count":155},{"id":"1805.07722","title":"Task-Agnostic Meta-Learning for Few-shot Learning","created":"2018-05-20","cited_by_count":151},{"id":"1906.05186","title":"Boosting Few-Shot Visual Learning with Self-Supervision","created":"2019-06-12","cited_by_count":140},{"id":"2002.12204","title":"Visual Commonsense R-CNN","created":"2020-02-27","cited_by_count":106},{"id":"1806.04734","title":"Delta-encoder: an effective sample synthesis method for few-shot object recognition","created":"2018-06-12","cited_by_count":89},{"id":"1502.08029","title":"Describing Videos by Exploiting Temporal Structure","created":"2015-02-27","cited_by_count":88},{"id":"1906.00562","title":"Learning to Self-Train for Semi-Supervised Few-Shot Classification","created":"2019-06-03","cited_by_count":83},{"id":"1603.06059","title":"Generating Natural Questions About an Image","created":"2016-03-19","cited_by_count":56},{"id":"2102.02751","title":"Semi-Supervised Action Recognition with Temporal Contrastive Learning","created":"2021-02-04","cited_by_count":50},{"id":"1911.06045","title":"Self-Supervised Learning For Few-Shot Image Classification","created":"2019-11-14","cited_by_count":44},{"id":"1709.07192","title":"Visual Question Generation as Dual Task of Visual Question Answering","created":"2017-09-21","cited_by_count":41},{"id":"1903.11207","title":"Information Maximizing Visual Question Generation","created":"2019-03-27","cited_by_count":40},{"id":"1511.05284","title":"Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data","created":"2015-11-17","cited_by_count":36},{"id":"2010.16010","title":"Loss re-scaling VQA: Revisiting the LanguagePrior Problem from a Class-imbalance View","created":"2020-10-30","cited_by_count":36},{"id":"1606.07770","title":"Captioning Images with Diverse Objects","created":"2016-06-24","cited_by_count":27},{"id":"1908.04289","title":"Multi-modality Latent Interaction Network for Visual Question Answering","created":"2019-08-10","cited_by_count":23},{"id":"1904.08482","title":"Variational Prototyping-Encoder: One-Shot Learning with Prototypical Images","created":"2019-04-17","cited_by_count":22},{"id":"1611.05546","title":"Zero-Shot Visual Question Answering","created":"2016-11-17","cited_by_count":20},{"id":"1703.08033","title":"Generative Adversarial Residual Pairwise Networks for One Shot Learning","created":"2017-03-23","cited_by_count":11},{"id":"1711.08105","title":"Visual Question Answering as a Meta Learning Task","created":"2017-11-22","cited_by_count":9},{"id":"2005.07771","title":"C3VQG: Category Consistent Cyclic Visual Question Generation","created":"2020-05-15","cited_by_count":8},{"id":"2008.05524","title":"Mitigating Dataset Imbalance via Joint Generation and Classification","created":"2020-08-12","cited_by_count":4}],"next_cursor":null}