{"list":"other","total":78,"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":"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":"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2104.08821","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","created":"2021-04-18","cited_by_count":2173},{"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":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"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":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"2106.12423","title":"Alias-Free Generative Adversarial Networks","created":"2021-06-23","cited_by_count":1184},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991},{"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":"1912.02164","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","created":"2019-12-04","cited_by_count":799},{"id":"1907.10786","title":"Interpreting the Latent Space of GANs for Semantic Face Editing","created":"2019-07-25","cited_by_count":695},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"1908.04319","title":"Neural Text Generation with Unlikelihood Training","created":"2019-08-12","cited_by_count":503},{"id":"1909.11059","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","created":"2019-09-24","cited_by_count":494},{"id":"2102.01454","title":"MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers","created":"2021-02-02","cited_by_count":470},{"id":"1704.06888","title":"Time-Contrastive Networks: Self-Supervised Learning from Video","created":"2017-04-23","cited_by_count":459},{"id":"1604.01696","title":"A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories","created":"2016-04-06","cited_by_count":417},{"id":"2107.06383","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","created":"2021-07-13","cited_by_count":321},{"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":"2202.06417","title":"A Contrastive Framework for Neural Text Generation","created":"2022-02-13","cited_by_count":225},{"id":"2111.12233","title":"Scaling Up Vision-Language Pre-training for Image Captioning","created":"2021-11-24","cited_by_count":196},{"id":"2102.10407","title":"VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning","created":"2021-02-20","cited_by_count":191},{"id":"1605.09304","title":"Synthesizing the preferred inputs for neurons in neural networks via deep generator networks","created":"2016-05-30","cited_by_count":181},{"id":"1511.07571","title":"DenseCap: Fully Convolutional Localization Networks for Dense Captioning","created":"2015-11-24","cited_by_count":176},{"id":"2004.03545","title":"Dense Regression Network for Video Grounding","created":"2020-04-07","cited_by_count":176},{"id":"2111.14447","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","created":"2021-11-29","cited_by_count":150},{"id":"2109.14739","title":"Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System","created":"2021-09-29","cited_by_count":139},{"id":"2106.01890","title":"SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization","created":"2021-06-03","cited_by_count":132},{"id":"2108.09980","title":"TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment","created":"2021-08-23","cited_by_count":102},{"id":"2104.08027","title":"Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders","created":"2021-04-16","cited_by_count":88},{"id":"1811.10787","title":"Unsupervised Image Captioning","created":"2018-11-27","cited_by_count":79},{"id":"1812.06587","title":"Grounded Video Description","created":"2018-12-17","cited_by_count":78},{"id":"2109.02492","title":"DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization","created":"2021-09-06","cited_by_count":72},{"id":"2109.07589","title":"CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning","created":"2021-09-15","cited_by_count":64},{"id":"1908.09317","title":"Towards Unsupervised Image Captioning with Shared Multimodal Embeddings","created":"2019-08-25","cited_by_count":54},{"id":"2108.13740","title":"Plan-then-Generate: Controlled Data-to-Text Generation via Planning","created":"2021-08-31","cited_by_count":52},{"id":"1810.10665","title":"Engaging Image Captioning Via Personality","created":"2018-10-25","cited_by_count":51},{"id":"1510.01431","title":"SentiCap: Generating Image Descriptions with Sentiments","created":"2015-10-06","cited_by_count":48},{"id":"2103.12204","title":"Human-like Controllable Image Captioning with Verb-specific Semantic Roles","created":"2021-03-22","cited_by_count":41},{"id":"2110.09753","title":"Unifying Multimodal Transformer for Bi-directional Image and Text Generation","created":"2021-10-19","cited_by_count":41},{"id":"2102.08220","title":"Non-Autoregressive Text Generation with Pre-trained Language Models","created":"2021-02-16","cited_by_count":36},{"id":"1903.05942","title":"Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning","created":"2019-03-14","cited_by_count":35},{"id":"2111.04198","title":"TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning","created":"2021-11-07","cited_by_count":32},{"id":"1904.01410","title":"Context and Attribute Grounded Dense Captioning","created":"2019-04-02","cited_by_count":31},{"id":"1807.03871","title":"\"Factual\" or \"Emotional\": Stylized Image Captioning with Adaptive Learning and Attention","created":"2018-07-10","cited_by_count":26},{"id":"2004.02214","title":"Prototype-to-Style: Dialogue Generation with Style-Aware Editing on Retrieval Memory","created":"2020-04-05","cited_by_count":22},{"id":"2108.12516","title":"Few-Shot Table-to-Text Generation with Prototype Memory","created":"2021-08-27","cited_by_count":21},{"id":"2110.08173","title":"Rewire-then-Probe: A Contrastive Recipe for Probing Biomedical Knowledge of Pre-trained Language Models","created":"2021-10-15","cited_by_count":21},{"id":"1410.1090","title":"Explain Images with Multimodal Recurrent Neural Networks","created":"2014-10-04","cited_by_count":15},{"id":"2104.13872","title":"Removing Word-Level Spurious Alignment between Images and Pseudo-Captions in Unsupervised Image Captioning","created":"2021-04-28","cited_by_count":14},{"id":"1809.00681","title":"Diverse and Coherent Paragraph Generation from Images","created":"2018-09-03","cited_by_count":13},{"id":"1806.06004","title":"Partially-Supervised Image Captioning","created":"2018-06-15","cited_by_count":11},{"id":"2110.06612","title":"Exploring Dense Retrieval for Dialogue Response Selection","created":"2021-10-13","cited_by_count":11}],"next_cursor":null}