{"list":"other","total":51,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"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":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"1612.00563","title":"Self-critical Sequence Training for Image Captioning","created":"2016-12-02","cited_by_count":547},{"id":"1803.08024","title":"Stacked Cross Attention for Image-Text Matching","created":"2018-03-21","cited_by_count":416},{"id":"1908.06954","title":"Attention on Attention for Image Captioning","created":"2019-08-19","cited_by_count":289},{"id":"2003.05176","title":"Equalization Loss for Long-Tailed Object Recognition","created":"2020-03-11","cited_by_count":285},{"id":"1812.02378","title":"Auto-Encoding Scene Graphs for Image Captioning","created":"2018-12-06","cited_by_count":255},{"id":"2007.09654","title":"Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets","created":"2020-07-19","cited_by_count":122},{"id":"1703.10660","title":"Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images","created":"2017-03-30","cited_by_count":101},{"id":"1412.6632","title":"Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)","created":"2014-12-20","cited_by_count":94},{"id":"1611.01646","title":"Boosting Image Captioning with Attributes","created":"2016-11-05","cited_by_count":76},{"id":"2102.12867","title":"FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation","created":"2021-02-25","cited_by_count":76},{"id":"1803.04376","title":"Discriminability objective for training descriptive captions","created":"2018-03-12","cited_by_count":67},{"id":"1703.06029","title":"Towards Diverse and Natural Image Descriptions via a Conditional GAN","created":"2017-03-17","cited_by_count":59},{"id":"1805.12589","title":"Fast, Diverse and Accurate Image Captioning Guided By Part-of-Speech","created":"2018-05-31","cited_by_count":55},{"id":"1710.02534","title":"Contrastive Learning for Image Captioning","created":"2017-10-06","cited_by_count":54},{"id":"1711.06420","title":"Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models","created":"2017-11-17","cited_by_count":53},{"id":"1711.09151","title":"Convolutional Image Captioning","created":"2017-11-24","cited_by_count":52},{"id":"1903.12020","title":"Describing like humans: on diversity in image captioning","created":"2019-03-28","cited_by_count":46},{"id":"1909.03918","title":"Hierarchy Parsing for Image Captioning","created":"2019-09-09","cited_by_count":44},{"id":"1701.02870","title":"Context-aware Captions from Context-agnostic Supervision","created":"2017-01-11","cited_by_count":43},{"id":"1807.09986","title":"Recurrent Fusion Network for Image Captioning","created":"2018-07-26","cited_by_count":43},{"id":"1802.01345","title":"DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Text","created":"2018-02-05","cited_by_count":40},{"id":"1803.08314","title":"Show, Tell and Discriminate: Image Captioning by Self-retrieval with Partially Labeled Data","created":"2018-03-22","cited_by_count":37},{"id":"1704.06485","title":"Attend to You: Personalized Image Captioning with Context Sequence Memory Networks","created":"2017-04-21","cited_by_count":35},{"id":"1709.03376","title":"Stack-Captioning: Coarse-to-Fine Learning for Image Captioning","created":"2017-09-11","cited_by_count":27},{"id":"2007.06877","title":"Compare and Reweight: Distinctive Image Captioning Using Similar Images Sets","created":"2020-07-14","cited_by_count":27},{"id":"2011.00966","title":"Diverse Image Captioning with Context-Object Split Latent Spaces","created":"2020-11-02","cited_by_count":22},{"id":"1908.08529","title":"Sequential Latent Spaces for Modeling the Intention During Diverse Image Captioning","created":"2019-08-22","cited_by_count":21},{"id":"2010.04924","title":"On Long-Tailed Phenomena in Neural Machine Translation","created":"2020-10-10","cited_by_count":20},{"id":"2003.03107","title":"Show, Edit and Tell: A Framework for Editing Image Captions","created":"2020-03-06","cited_by_count":18},{"id":"2004.03708","title":"Context-Aware Group Captioning via Self-Attention and Contrastive Features","created":"2020-04-07","cited_by_count":17},{"id":"1805.07112","title":"Improving Image Captioning with Conditional Generative Adversarial Nets","created":"2018-05-18","cited_by_count":14},{"id":"1805.09019","title":"CNN+CNN: Convolutional Decoders for Image Captioning","created":"2018-05-23","cited_by_count":9},{"id":"1804.00861","title":"Generating Diverse and Accurate Visual Captions by Comparative Adversarial Learning","created":"2018-04-03","cited_by_count":7},{"id":"1908.04919","title":"Towards Diverse and Accurate Image Captions via Reinforcing Determinantal Point Process","created":"2019-08-14","cited_by_count":4}],"next_cursor":null}