{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"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":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2006.09011","title":"Improved Techniques for Training Score-Based Generative Models","created":"2020-06-16","cited_by_count":1043},{"id":"2201.11793","title":"Denoising Diffusion Restoration Models","created":"2022-01-27","cited_by_count":963},{"id":"2302.03011","title":"Structure and Content-Guided Video Synthesis with Diffusion Models","created":"2023-02-06","cited_by_count":590},{"id":"2401.09047","title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","created":"2024-01-17","cited_by_count":579},{"id":"2208.04202","title":"Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning","created":"2022-08-08","cited_by_count":373},{"id":"1609.08675","title":"YouTube-8M: A Large-Scale Video Classification Benchmark","created":"2016-09-27","cited_by_count":324},{"id":"2303.12688","title":"Pix2Video: Video Editing using Image Diffusion","created":"2023-03-22","cited_by_count":320},{"id":"2112.05146","title":"Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction","created":"2021-12-09","cited_by_count":307},{"id":"2312.06662","title":"Photorealistic Video Generation with Diffusion Models","created":"2023-12-11","cited_by_count":306},{"id":"2212.09478","title":"MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation","created":"2022-12-19","cited_by_count":227},{"id":"2308.09592","title":"StableVideo: Text-driven Consistency-aware Diffusion Video Editing","created":"2023-08-18","cited_by_count":183},{"id":"2210.00939","title":"Improving Sample Quality of Diffusion Models Using Self-Attention Guidance","created":"2022-10-03","cited_by_count":154},{"id":"1605.08110","title":"Video Summarization with Long Short-term Memory","created":"2016-05-26","cited_by_count":142},{"id":"2206.07696","title":"Diffusion Models for Video Prediction and Infilling","created":"2022-06-15","cited_by_count":135},{"id":"2107.00650","title":"CLIP-It! Language-Guided Video Summarization","created":"2021-07-01","cited_by_count":99},{"id":"2312.03816","title":"AVID: Any-Length Video Inpainting with Diffusion Model","created":"2023-12-06","cited_by_count":82},{"id":"2303.17959","title":"Diffusion Action Segmentation","created":"2023-03-31","cited_by_count":74},{"id":"1812.01969","title":"Summarizing Videos with Attention","created":"2018-12-05","cited_by_count":69},{"id":"2303.07284","title":"Align and Attend: Multimodal Summarization with Dual Contrastive Losses","created":"2023-03-13","cited_by_count":65},{"id":"1903.11328","title":"Rethinking the Evaluation of Video Summaries","created":"2019-03-27","cited_by_count":62},{"id":"2307.02869","title":"MomentDiff: Generative Video Moment Retrieval from Random to Real","created":"2023-07-06","cited_by_count":58},{"id":"2311.18830","title":"MotionEditor: Editing Video Motion via Content-Aware Diffusion","created":"2023-11-30","cited_by_count":57},{"id":"1904.12251","title":"Hierarchical Recurrent Neural Network for Video Summarization","created":"2019-04-28","cited_by_count":44},{"id":"2007.09833","title":"MINI-Net: Multiple Instance Ranking Network for Video Highlight Detection","created":"2020-07-20","cited_by_count":42},{"id":"2108.11770","title":"Cross-category Video Highlight Detection via Set-based Learning","created":"2021-08-26","cited_by_count":38},{"id":"1805.12174","title":"Video Summarization by Learning from Unpaired Data","created":"2018-05-30","cited_by_count":36},{"id":"2009.10942","title":"Exploring global diverse attention via pairwise temporal relation for video summarization","created":"2020-09-23","cited_by_count":29},{"id":"2403.12042","title":"Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation","created":"2024-03-18","cited_by_count":27},{"id":"2104.11530","title":"Supervised Video Summarization via Multiple Feature Sets with Parallel Attention","created":"2021-04-23","cited_by_count":26},{"id":"2104.12465","title":"GPT2MVS: Generative Pre-trained Transformer-2 for Multi-modal Video Summarization","created":"2021-04-26","cited_by_count":26},{"id":"2405.11905","title":"CSTA: CNN-based Spatiotemporal Attention for Video Summarization","created":"2024-05-20","cited_by_count":23},{"id":"2407.11451","title":"Isometric Representation Learning for Disentangled Latent Space of Diffusion Models","created":"2024-07-16","cited_by_count":22},{"id":"2201.02494","title":"Progressive Video Summarization via Multimodal Self-supervised Learning","created":"2022-01-07","cited_by_count":21},{"id":"2109.10559","title":"Hierarchical Multimodal Transformer to Summarize Videos","created":"2021-09-22","cited_by_count":19},{"id":"2305.06594","title":"V2Meow: Meowing to the Visual Beat via Video-to-Music Generation","created":"2023-05-11","cited_by_count":18},{"id":"1706.03114","title":"Collaborative Summarization of Topic-Related Videos","created":"2017-06-09","cited_by_count":17},{"id":"2008.08360","title":"Query Twice: Dual Mixture Attention Meta Learning for Video Summarization","created":"2020-08-19","cited_by_count":14},{"id":"2112.13478","title":"Video Joint Modelling Based on Hierarchical Transformer for Co-summarization","created":"2021-12-27","cited_by_count":10},{"id":"2505.00502","title":"Towards Scalable Human-aligned Benchmark for Text-guided Image Editing","created":"2025-05-01","cited_by_count":7},{"id":"1906.02792","title":"Attention is all you need for Videos: Self-attention based Video Summarization using Universal Transformers","created":"2019-06-06","cited_by_count":4},{"id":"2412.04746","title":"Diff4Steer: Steerable Diffusion Prior for Generative Music Retrieval with Semantic Guidance","created":"2024-12-06","cited_by_count":3}],"next_cursor":null}