{"list":"other","total":67,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"1609.04802","title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","created":"2016-09-15","cited_by_count":1908},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"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":"2003.00196","title":"First Order Motion Model for Image Animation","created":"2020-02-29","cited_by_count":704},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"1908.08345","title":"Text Summarization with Pretrained Encoders","created":"2019-08-22","cited_by_count":556},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"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":"2410.05954","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","created":"2024-10-08","cited_by_count":366},{"id":"2309.15103","title":"LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models","created":"2023-09-26","cited_by_count":349},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"2303.08320","title":"VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation","created":"2023-03-15","cited_by_count":331},{"id":"2408.14837","title":"Diffusion Models Are Real-Time Game Engines","created":"2024-08-27","cited_by_count":296},{"id":"1605.07157","title":"Unsupervised Learning for Physical Interaction through Video Prediction","created":"2016-05-23","cited_by_count":260},{"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":"2111.10337","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","created":"2021-11-19","cited_by_count":226},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"2312.04433","title":"DreamVideo: Composing Your Dream Videos with Customized Subject and Motion","created":"2023-12-07","cited_by_count":188},{"id":"2304.08477","title":"Latent-Shift: Latent Diffusion with Temporal Shift for Efficient Text-to-Video Generation","created":"2023-04-17","cited_by_count":137},{"id":"2405.11473","title":"FIFO-Diffusion: Generating Infinite Videos from Text without Training","created":"2024-05-19","cited_by_count":137},{"id":"1604.02748","title":"TGIF: A New Dataset and Benchmark on Animated GIF Description","created":"2016-04-10","cited_by_count":124},{"id":"1803.02991","title":"Disentangled Sequential Autoencoder","created":"2018-03-08","cited_by_count":120},{"id":"1704.05831","title":"Learning to Generate Long-term Future via Hierarchical Prediction","created":"2017-04-19","cited_by_count":88},{"id":"2309.14494","title":"Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator","created":"2023-09-25","cited_by_count":74},{"id":"2304.06632","title":"AI-Generated Content (AIGC): A Survey","created":"2023-03-26","cited_by_count":59},{"id":"2406.04277","title":"VideoTetris: Towards Compositional Text-to-Video Generation","created":"2024-06-06","cited_by_count":51},{"id":"2405.10674","title":"From Sora What We Can See: A Survey of Text-to-Video Generation","created":"2024-05-17","cited_by_count":27},{"id":"2212.07849","title":"DETR4D: Direct Multi-View 3D Object Detection with Sparse Attention","created":"2022-12-15","cited_by_count":21},{"id":"2404.00234","title":"Grid Diffusion Models for Text-to-Video Generation","created":"2024-03-30","cited_by_count":21},{"id":"2305.18303","title":"New Era of Artificial Intelligence in Education: Towards a Sustainable Multifaceted Revolution","created":"2023-05-12","cited_by_count":20},{"id":"2311.06329","title":"A Survey of AI Text-to-Image and AI Text-to-Video Generators","created":"2023-11-10","cited_by_count":17},{"id":"1811.10670","title":"AI Fairness for People with Disabilities: Point of View","created":"2018-11-26","cited_by_count":16},{"id":"2407.14971","title":"Sim-CLIP: Unsupervised Siamese Adversarial Fine-Tuning for Robust and Semantically-Rich Vision-Language Models","created":"2024-07-20","cited_by_count":12},{"id":"2403.15586","title":"Generative AI in Education: A Study of Educators' Awareness, Sentiments, and Influencing Factors","created":"2024-03-22","cited_by_count":10},{"id":"2407.01921","title":"GVDIFF: Grounded Text-to-Video Generation with Diffusion Models","created":"2024-07-02","cited_by_count":4},{"id":"2410.10927","title":"Cultural Heritage 3D Reconstruction with Diffusion Networks","created":"2024-10-14","cited_by_count":4},{"id":"2411.01228","title":"The Interaction Layer: An Exploration for Co-Designing User-LLM Interactions in Parental Wellbeing Support Systems","created":"2024-11-02","cited_by_count":3},{"id":"2212.06232","title":"Synthetic Image Data for Deep Learning","created":"2022-12-12","cited_by_count":2},{"id":"2312.02725","title":"R3D-SWIN:Use Shifted Window Attention for Single-View 3D Reconstruction","created":"2023-12-05","cited_by_count":1},{"id":"2406.15383","title":"Artificial Intelligence, VR, AR and Metaverse Technologies for Human Resources Management","created":"2024-04-19","cited_by_count":1},{"id":"2409.18458","title":"Enhancing Crime Scene Investigations through Virtual Reality and Deep Learning Techniques","created":"2024-09-27","cited_by_count":1}],"next_cursor":null}