{"list":"other","total":62,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"2008.10010","title":"A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild","created":"2020-08-23","cited_by_count":672},{"id":"1906.08172","title":"MediaPipe: A Framework for Building Perception Pipelines","created":"2019-06-14","cited_by_count":583},{"id":"1802.00434","title":"DensePose: Dense Human Pose Estimation In The Wild","created":"2018-02-01","cited_by_count":575},{"id":"2212.04048","title":"Executing your Commands via Motion Diffusion in Latent Space","created":"2022-12-08","cited_by_count":575},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"1808.06601","title":"Video-to-Video Synthesis","created":"2018-08-20","cited_by_count":390},{"id":"1609.02612","title":"Generating Videos with Scene Dynamics","created":"2016-09-08","cited_by_count":376},{"id":"1808.07371","title":"Everybody Dance Now","created":"2018-08-22","cited_by_count":315},{"id":"2003.13830","title":"Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation","created":"2020-03-30","cited_by_count":256},{"id":"1705.09368","title":"Pose Guided Person Image Generation","created":"2017-05-25","cited_by_count":251},{"id":"1912.05566","title":"Neural Voice Puppetry: Audio-driven Facial Reenactment","created":"2019-12-11","cited_by_count":250},{"id":"2004.11660","title":"Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning","created":"2020-04-24","cited_by_count":220},{"id":"1910.12713","title":"Few-shot Video-to-Video Synthesis","created":"2019-10-28","cited_by_count":197},{"id":"2212.03551","title":"Talking About Large Language Models","created":"2022-12-07","cited_by_count":175},{"id":"2008.08143","title":"How2Sign: A Large-scale Multimodal Dataset for Continuous American Sign Language","created":"2020-08-18","cited_by_count":173},{"id":"1801.00055","title":"Deformable GANs for Pose-based Human Image Generation","created":"2017-12-29","cited_by_count":166},{"id":"2309.17448","title":"SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation","created":"2023-09-29","cited_by_count":155},{"id":"1904.03349","title":"Progressive Pose Attention Transfer for Person Image Generation","created":"2019-04-06","cited_by_count":138},{"id":"2004.14874","title":"Progressive Transformers for End-to-End Sign Language Production","created":"2020-04-30","cited_by_count":120},{"id":"1804.07739","title":"Synthesizing Images of Humans in Unseen Poses","created":"2018-04-20","cited_by_count":97},{"id":"1801.10111","title":"Video-based Sign Language Recognition without Temporal Segmentation","created":"2018-01-30","cited_by_count":88},{"id":"2007.09278","title":"XingGAN for Person Image Generation","created":"2020-07-17","cited_by_count":81},{"id":"2008.00932","title":"AUTSL: A Large Scale Multi-modal Turkish Sign Language Dataset and Baseline Methods","created":"2020-08-03","cited_by_count":75},{"id":"2205.12870","title":"Open-Domain Sign Language Translation Learned from Online Video","created":"2022-05-25","cited_by_count":72},{"id":"2007.08509","title":"World-Consistent Video-to-Video Synthesis","created":"2020-07-16","cited_by_count":69},{"id":"1811.11436","title":"Neural Sign Language Translation based on Human Keypoint Estimation","created":"2018-11-28","cited_by_count":65},{"id":"2005.02671","title":"CONFIG: Controllable Neural Face Image Generation","created":"2020-05-06","cited_by_count":61},{"id":"2203.15354","title":"Signing at Scale: Learning to Co-Articulate Signs for Large-Scale Photo-Realistic Sign Language Production","created":"2022-03-29","cited_by_count":61},{"id":"2008.12405","title":"Adversarial Training for Multi-Channel Sign Language Production","created":"2020-08-27","cited_by_count":57},{"id":"2008.09918","title":"Quantitative Survey of the State of the Art in Sign Language Recognition","created":"2020-08-22","cited_by_count":50},{"id":"2103.06982","title":"Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks","created":"2021-03-11","cited_by_count":50},{"id":"2107.11317","title":"Mixed SIGNals: Sign Language Production via a Mixture of Motion Primitives","created":"2021-07-23","cited_by_count":50},{"id":"2312.02702","title":"Neural Sign Actors: A diffusion model for 3D sign language production from text","created":"2023-12-05","cited_by_count":49},{"id":"2005.06734","title":"Dense-Resolution Network for Point Cloud Classification and Segmentation","created":"2020-05-14","cited_by_count":45},{"id":"1907.12484","title":"Joey NMT: A Minimalist NMT Toolkit for Novices","created":"2019-07-29","cited_by_count":39},{"id":"2304.06371","title":"Sign Language Translation from Instructional Videos","created":"2023-04-13","cited_by_count":39},{"id":"1904.00129","title":"Dance Dance Generation: Motion Transfer for Internet Videos","created":"2019-03-30","cited_by_count":28},{"id":"1808.04859","title":"GestureGAN for Hand Gesture-to-Gesture Translation in the Wild","created":"2018-08-14","cited_by_count":27},{"id":"2104.14631","title":"Text2Video: Text-driven Talking-head Video Synthesis with Personalized Phoneme-Pose Dictionary","created":"2021-04-29","cited_by_count":27},{"id":"2312.05107","title":"DreaMoving: A Human Video Generation Framework based on Diffusion Models","created":"2023-12-08","cited_by_count":25},{"id":"2311.10174","title":"JWSign: A Highly Multilingual Corpus of Bible Translations for more Diversity in Sign Language Processing","created":"2023-11-16","cited_by_count":18},{"id":"1911.10672","title":"GAC-GAN: A General Method for Appearance-Controllable Human Video Motion Transfer","created":"2019-11-25","cited_by_count":14},{"id":"2012.10941","title":"Can Everybody Sign Now? Exploring Sign Language Video Generation from 2D Poses","created":"2020-12-20","cited_by_count":12},{"id":"2112.05277","title":"Skeletal Graph Self-Attention: Embedding a Skeleton Inductive Bias into Sign Language Production","created":"2021-12-06","cited_by_count":11},{"id":"1907.05916","title":"Gesture-to-Gesture Translation in the Wild via Category-Independent Conditional Maps","created":"2019-07-12","cited_by_count":7}],"next_cursor":null}