{"list":"other","total":66,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"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":"1411.1792","title":"How transferable are features in deep neural networks?","created":"2014-11-06","cited_by_count":1225},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991},{"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":"1912.02164","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","created":"2019-12-04","cited_by_count":799},{"id":"1909.05858","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","created":"2019-09-11","cited_by_count":762},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"1812.08658","title":"nocaps: novel object captioning at scale","created":"2018-12-20","cited_by_count":444},{"id":"1609.05473","title":"SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient","created":"2016-09-18","cited_by_count":376},{"id":"1912.08226","title":"Meshed-Memory Transformer for Image Captioning","created":"2019-12-17","cited_by_count":343},{"id":"1608.00187","title":"Visual Relationship Detection with Language Priors","created":"2016-07-31","cited_by_count":334},{"id":"2107.06383","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","created":"2021-07-13","cited_by_count":321},{"id":"1703.00955","title":"Toward Controlled Generation of Text","created":"2017-03-02","cited_by_count":272},{"id":"1812.02378","title":"Auto-Encoding Scene Graphs for Image Captioning","created":"2018-12-06","cited_by_count":255},{"id":"2110.02624","title":"CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation","created":"2021-10-06","cited_by_count":254},{"id":"1705.09655","title":"Style Transfer from Non-Parallel Text by Cross-Alignment","created":"2017-05-26","cited_by_count":248},{"id":"1612.01887","title":"Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning","created":"2016-12-06","cited_by_count":232},{"id":"1909.11740","title":"UNITER: UNiversal Image-TExt Representation Learning","created":"2019-09-25","cited_by_count":228},{"id":"1809.07041","title":"Exploring Visual Relationship for Image Captioning","created":"2018-09-19","cited_by_count":215},{"id":"2003.14080","title":"X-Linear Attention Networks for Image Captioning","created":"2020-03-31","cited_by_count":198},{"id":"1906.05963","title":"Image Captioning: Transforming Objects into Words","created":"2019-06-14","cited_by_count":171},{"id":"1803.09845","title":"Neural Baby Talk","created":"2018-03-27","cited_by_count":107},{"id":"1612.00576","title":"Guided Open Vocabulary Image Captioning with Constrained Beam Search","created":"2016-12-02","cited_by_count":105},{"id":"1610.00388","title":"Learning to Translate in Real-time with Neural Machine Translation","created":"2016-10-03","cited_by_count":97},{"id":"1412.6632","title":"Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)","created":"2014-12-20","cited_by_count":94},{"id":"1811.10787","title":"Unsupervised Image Captioning","created":"2018-11-27","cited_by_count":79},{"id":"2101.06462","title":"Dual-Level Collaborative Transformer for Image Captioning","created":"2021-01-16","cited_by_count":71},{"id":"2003.08897","title":"Normalized and Geometry-Aware Self-Attention Network for Image Captioning","created":"2020-03-19","cited_by_count":63},{"id":"2010.10802","title":"Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies","created":"2020-10-21","cited_by_count":57},{"id":"1908.09317","title":"Towards Unsupervised Image Captioning with Shared Multimodal Embeddings","created":"2019-08-25","cited_by_count":54},{"id":"1711.09151","title":"Convolutional Image Captioning","created":"2017-11-24","cited_by_count":52},{"id":"1904.05876","title":"A Simple Baseline for Audio-Visual Scene-Aware Dialog","created":"2019-04-11","cited_by_count":52},{"id":"2012.07061","title":"Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer Network","created":"2020-12-13","cited_by_count":48},{"id":"1904.05880","title":"Factor Graph Attention","created":"2019-04-11","cited_by_count":41},{"id":"2110.12427","title":"Image-Based CLIP-Guided Essence Transfer","created":"2021-10-24","cited_by_count":39},{"id":"1511.05284","title":"Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data","created":"2015-11-17","cited_by_count":36},{"id":"2110.14375","title":"Perceptual Score: What Data Modalities Does Your Model Perceive?","created":"2021-10-27","cited_by_count":35},{"id":"1711.07068","title":"Diverse and Accurate Image Description Using a Variational Auto-Encoder with an Additive Gaussian Encoding Space","created":"2017-11-19","cited_by_count":33},{"id":"1909.02201","title":"Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach","created":"2019-09-05","cited_by_count":30},{"id":"1606.07770","title":"Captioning Images with Diverse Objects","created":"2016-06-24","cited_by_count":27},{"id":"1709.03376","title":"Stack-Captioning: Coarse-to-Fine Learning for Image Captioning","created":"2017-09-11","cited_by_count":27},{"id":"1711.04323","title":"High-Order Attention Models for Visual Question Answering","created":"2017-11-12","cited_by_count":22},{"id":"2102.03054","title":"Removing biased data to improve fairness and accuracy","created":"2021-02-05","cited_by_count":17},{"id":"1411.7399","title":"Fisher Vectors Derived from Hybrid Gaussian-Laplacian Mixture Models for Image Annotation","created":"2014-11-26","cited_by_count":16},{"id":"1904.11251","title":"Pointing Novel Objects in Image Captioning","created":"2019-04-25","cited_by_count":15},{"id":"1809.00681","title":"Diverse and Coherent Paragraph Generation from Images","created":"2018-09-03","cited_by_count":13},{"id":"1804.07915","title":"A Stable and Effective Learning Strategy for Trainable Greedy Decoding","created":"2018-04-21","cited_by_count":12},{"id":"1908.02726","title":"Cascaded Revision Network for Novel Object Captioning","created":"2019-08-06","cited_by_count":5}],"next_cursor":null}