{"list":"other","total":52,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"id":"1602.00763","title":"Simple Online and Realtime Tracking","created":"2016-02-02","cited_by_count":868},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"1706.08612","title":"VoxCeleb: a large-scale speaker identification dataset","created":"2017-06-26","cited_by_count":732},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"1708.03985","title":"AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild","created":"2017-08-14","cited_by_count":492},{"id":"2210.02399","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","created":"2022-10-05","cited_by_count":484},{"id":"1904.03493","title":"VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research","created":"2019-04-06","cited_by_count":414},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"2112.14683","title":"StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2","created":"2021-12-29","cited_by_count":301},{"id":"2205.11495","title":"Flexible Diffusion Modeling of Long Videos","created":"2022-05-23","cited_by_count":294},{"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":"2207.12393","title":"CelebV-HQ: A Large-Scale Video Facial Attributes Dataset","created":"2022-07-25","cited_by_count":250},{"id":"2106.11097","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","created":"2021-06-21","cited_by_count":225},{"id":"1903.08225","title":"Cross-task weakly supervised learning from instructional videos","created":"2019-03-19","cited_by_count":199},{"id":"2202.10571","title":"Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks","created":"2022-02-21","cited_by_count":186},{"id":"1908.00375","title":"Quality Assessment of In-the-Wild Videos","created":"2019-08-01","cited_by_count":164},{"id":"2104.15069","title":"A Good Image Generator Is What You Need for High-Resolution Video Synthesis","created":"2021-04-30","cited_by_count":163},{"id":"1909.12224","title":"Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis","created":"2019-09-26","cited_by_count":161},{"id":"1710.00421","title":"Video Generation From Text","created":"2017-10-01","cited_by_count":154},{"id":"1803.09179","title":"FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces","created":"2018-03-24","cited_by_count":119},{"id":"1506.09215","title":"Unsupervised Learning from Narrated Instruction Videos","created":"2015-06-30","cited_by_count":116},{"id":"1810.07212","title":"Cross-Modal and Hierarchical Modeling of Video and Text","created":"2018-10-16","cited_by_count":103},{"id":"1412.6604","title":"Video (language) modeling: a baseline for generative models of natural videos","created":"2014-12-20","cited_by_count":92},{"id":"2112.02815","title":"Make It Move: Controllable Image-to-Video Generation with Text Descriptions","created":"2021-12-06","cited_by_count":88},{"id":"1807.11079","title":"ReenactGAN: Learning to Reenact Faces via Boundary Transfer","created":"2018-07-29","cited_by_count":85},{"id":"1804.08264","title":"To Create What You Tell: Generating Videos from Captions","created":"2018-04-23","cited_by_count":84},{"id":"2207.09814","title":"NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis","created":"2022-07-20","cited_by_count":71},{"id":"1804.03608","title":"Imagine This! Scripts to Compositions to Videos","created":"2018-04-10","cited_by_count":54},{"id":"1611.10314","title":"Sync-DRAW: Automatic Video Generation using Deep Recurrent Attentive Architectures","created":"2016-11-30","cited_by_count":44},{"id":"2203.02573","title":"Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning","created":"2022-03-04","cited_by_count":37},{"id":"1503.01558","title":"What's Cookin'? Interpreting Cooking Videos using Text, Speech and Vision","created":"2015-03-05","cited_by_count":31},{"id":"2005.04909","title":"Conditional Image Generation and Manipulation for User-Specified Content","created":"2020-05-11","cited_by_count":20},{"id":"2204.08058","title":"MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration","created":"2022-04-17","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}],"next_cursor":null}