{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"1904.05068","title":"Relational Knowledge Distillation","created":"2019-04-10","cited_by_count":889},{"id":"1910.10699","title":"Contrastive Representation Distillation","created":"2019-10-23","cited_by_count":748},{"id":"1605.05396","title":"Generative Adversarial Text to Image Synthesis","created":"2016-05-17","cited_by_count":735},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"1711.10485","title":"AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks","created":"2017-11-28","cited_by_count":664},{"id":"1809.06839","title":"Albumentations: fast and flexible image augmentations","created":"2018-09-18","cited_by_count":560},{"id":"2203.13131","title":"Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors","created":"2022-03-24","cited_by_count":487},{"id":"2210.02399","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","created":"2022-10-05","cited_by_count":484},{"id":"2003.12462","title":"TextCaps: a Dataset for Image Captioning with Reading Comprehension","created":"2020-03-24","cited_by_count":400},{"id":"1904.01310","title":"DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis","created":"2019-04-02","cited_by_count":308},{"id":"2204.14217","title":"CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers","created":"2022-04-28","cited_by_count":307},{"id":"2104.09044","title":"Distilling Knowledge via Knowledge Review","created":"2021-04-19","cited_by_count":288},{"id":"2104.14806","title":"GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions","created":"2021-04-30","cited_by_count":256},{"id":"2111.12417","title":"N\\\"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion","created":"2021-11-24","cited_by_count":253},{"id":"1803.10837","title":"Learning Deep Representations with Probabilistic Knowledge Transfer","created":"2018-03-28","cited_by_count":213},{"id":"1604.03968","title":"Visual Storytelling","created":"2016-04-13","cited_by_count":176},{"id":"1710.00421","title":"Video Generation From Text","created":"2017-10-01","cited_by_count":154},{"id":"1812.02784","title":"StoryGAN: A Sequential Conditional GAN for Story Visualization","created":"2018-12-06","cited_by_count":138},{"id":"1902.05660","title":"Cycle-Consistency for Robust Visual Question Answering","created":"2019-02-15","cited_by_count":105},{"id":"1804.08264","title":"To Create What You Tell: Generating Videos from Captions","created":"2018-04-23","cited_by_count":84},{"id":"1809.05375","title":"Style Augmentation: Data Augmentation via Style Randomization","created":"2018-09-14","cited_by_count":79},{"id":"2005.05402","title":"MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning","created":"2020-05-11","cited_by_count":79},{"id":"2209.06192","title":"StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation","created":"2022-09-13","cited_by_count":74},{"id":"1707.00836","title":"DeepStory: Video Story QA by Deep Embedded Memory Networks","created":"2017-07-04","cited_by_count":68},{"id":"1804.03608","title":"Imagine This! Scripts to Compositions to Videos","created":"2018-04-10","cited_by_count":54},{"id":"2110.10834","title":"Integrating Visuospatial, Linguistic and Commonsense Structure into Story Visualization","created":"2021-10-21","cited_by_count":52},{"id":"1611.10314","title":"Sync-DRAW: Automatic Video Generation using Deep Recurrent Attentive Architectures","created":"2016-11-30","cited_by_count":44},{"id":"2105.10026","title":"Improving Generation and Evaluation of Visual Stories via Semantic Consistency","created":"2021-05-20","cited_by_count":43},{"id":"1808.07632","title":"DOPING: Generative Data Augmentation for Unsupervised Anomaly Detection with GAN","created":"2018-08-23","cited_by_count":34},{"id":"2210.08465","title":"Character-Centric Story Visualization via Visual Planning and Token Alignment","created":"2022-10-16","cited_by_count":33},{"id":"2007.09271","title":"OnlineAugment: Online Data Augmentation with Less Domain Knowledge","created":"2020-07-17","cited_by_count":28},{"id":"2006.14699","title":"Learning Data Augmentation with Online Bilevel Optimization for Image Classification","created":"2020-06-25","cited_by_count":20},{"id":"2009.02018","title":"TiVGAN: Text to Image to Video Generation with Step-by-Step Evolutionary Generator","created":"2020-09-04","cited_by_count":19},{"id":"2111.11133","title":"L-Verse: Bidirectional Generation Between Image and Text","created":"2021-11-22","cited_by_count":15},{"id":"1805.01123","title":"MC-GAN: Multi-conditional Generative Adversarial Network for Image Synthesis","created":"2018-05-03","cited_by_count":10}],"next_cursor":null}