{"list":"other","total":91,"rows":[{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"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":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"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":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"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":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"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":"2302.08453","title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","created":"2023-02-16","cited_by_count":1351},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"2211.12572","title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","created":"2022-11-22","cited_by_count":906},{"id":"2310.04378","title":"Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference","created":"2023-10-06","cited_by_count":846},{"id":"1710.09829","title":"Dynamic Routing Between Capsules","created":"2017-10-26","cited_by_count":689},{"id":"2303.13439","title":"Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators","created":"2023-03-23","cited_by_count":670},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"2308.06571","title":"ModelScope Text-to-Video Technical Report","created":"2023-08-12","cited_by_count":658},{"id":"2210.11427","title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","created":"2022-10-20","cited_by_count":647},{"id":"2108.02938","title":"ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models","created":"2021-08-06","cited_by_count":635},{"id":"2302.03011","title":"Structure and Content-Guided Video Synthesis with Diffusion Models","created":"2023-02-06","cited_by_count":590},{"id":"2310.19512","title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","created":"2023-10-30","cited_by_count":535},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2211.07600","title":"Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures","created":"2022-11-14","cited_by_count":506},{"id":"2310.12190","title":"DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors","created":"2023-10-18","cited_by_count":471},{"id":"2211.11018","title":"MagicVideo: Efficient Video Generation With Latent Diffusion Models","created":"2022-11-20","cited_by_count":465},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"2307.10373","title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","created":"2023-07-19","cited_by_count":442},{"id":"2302.13848","title":"ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation","created":"2023-02-27","cited_by_count":416},{"id":"2211.13221","title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","created":"2022-11-23","cited_by_count":388},{"id":"2309.15103","title":"LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models","created":"2023-09-26","cited_by_count":349},{"id":"2304.03411","title":"InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning","created":"2023-04-06","cited_by_count":345},{"id":"2303.11305","title":"SVDiff: Compact Parameter Space for Diffusion Fine-Tuning","created":"2023-03-20","cited_by_count":338},{"id":"2112.03221","title":"Text2Mesh: Text-Driven Neural Stylization for Meshes","created":"2021-12-06","cited_by_count":334},{"id":"1704.03477","title":"A Neural Representation of Sketch Drawings","created":"2017-04-11","cited_by_count":313},{"id":"2112.00390","title":"SegDiff: Image Segmentation with Diffusion Probabilistic Models","created":"2021-12-01","cited_by_count":280},{"id":"2104.14806","title":"GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions","created":"2021-04-30","cited_by_count":256},{"id":"2303.09522","title":"P+: Extended Textual Conditioning in Text-to-Image Generation","created":"2023-03-16","cited_by_count":242},{"id":"2209.02646","title":"A Survey on Generative Diffusion Model","created":"2022-09-06","cited_by_count":240},{"id":"1710.11252","title":"Stochastic Variational Video Prediction","created":"2017-10-30","cited_by_count":234},{"id":"2301.11280","title":"Text-To-4D Dynamic Scene Generation","created":"2023-01-26","cited_by_count":205},{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204},{"id":"2302.12228","title":"Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models","created":"2023-02-23","cited_by_count":203},{"id":"1411.2539","title":"Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models","created":"2014-11-10","cited_by_count":198},{"id":"2305.01644","title":"Key-Locked Rank One Editing for Text-to-Image Personalization","created":"2023-05-02","cited_by_count":194},{"id":"1906.02634","title":"Scaling Autoregressive Video Models","created":"2019-06-06","cited_by_count":190},{"id":"2106.14843","title":"CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders","created":"2021-06-28","cited_by_count":187},{"id":"2303.13744","title":"Conditional Image-to-Video Generation with Latent Flow Diffusion Models","created":"2023-03-24","cited_by_count":181},{"id":"2007.11301","title":"DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation","created":"2020-07-22","cited_by_count":159},{"id":"2204.02849","title":"KNN-Diffusion: Image Generation via Large-Scale Retrieval","created":"2022-04-06","cited_by_count":137},{"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":"2103.05180","title":"An Introduction to Deep Generative Modeling","created":"2021-03-09","cited_by_count":104},{"id":"1406.5679","title":"Deep Fragment Embeddings for Bidirectional Image Sentence Mapping","created":"2014-06-22","cited_by_count":99},{"id":"2303.13495","title":"ReVersion: Diffusion-Based Relation Inversion from Images","created":"2023-03-23","cited_by_count":82},{"id":"2206.04655","title":"Towards Layer-wise Image Vectorization","created":"2022-06-09","cited_by_count":79},{"id":"2309.00398","title":"VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generation","created":"2023-09-01","cited_by_count":74},{"id":"1804.01118","title":"Synthesizing Programs for Images using Reinforced Adversarial Learning","created":"2018-04-03","cited_by_count":72},{"id":"1901.00542","title":"Photo-Sketching: Inferring Contour Drawings from Images","created":"2019-01-02","cited_by_count":68},{"id":"2001.02600","title":"Deep Learning for Free-Hand Sketch: A Survey","created":"2020-01-08","cited_by_count":59},{"id":"2203.14713","title":"Image-text Retrieval: A Survey on Recent Research and Development","created":"2022-03-28","cited_by_count":55},{"id":"1805.00247","title":"Learning to Sketch with Shortcut Cycle Consistency","created":"2018-05-01","cited_by_count":47},{"id":"1603.07063","title":"Semantic Object Parsing with Graph LSTM","created":"2016-03-23","cited_by_count":44},{"id":"2109.08857","title":"Modern Evolution Strategies for Creativity: Fitting Concrete Images and Abstract Concepts","created":"2021-09-18","cited_by_count":40},{"id":"1804.04804","title":"Learning Deep Sketch Abstraction","created":"2018-04-13","cited_by_count":36},{"id":"2212.04473","title":"Diffusion Guided Domain Adaptation of Image Generators","created":"2022-12-08","cited_by_count":35},{"id":"2106.02067","title":"Learning to Draw: Emergent Communication through Sketching","created":"2021-06-03","cited_by_count":23},{"id":"2304.11603","title":"LaMD: Latent Motion Diffusion for Image-Conditional Video Generation","created":"2023-04-23","cited_by_count":22},{"id":"2310.07653","title":"Mini-DALLE3: Interactive Text to Image by Prompting Large Language Models","created":"2023-10-11","cited_by_count":22},{"id":"1910.01007","title":"Unsupervised Doodling and Painting with Improved SPIRAL","created":"2019-10-02","cited_by_count":21},{"id":"2103.16194","title":"Differentiable Drawing and Sketching","created":"2021-03-30","cited_by_count":21},{"id":"1709.04121","title":"Sketch-pix2seq: a Model to Generate Sketches of Multiple Categories","created":"2017-09-13","cited_by_count":20},{"id":"2203.16639","title":"FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations","created":"2022-03-30","cited_by_count":20},{"id":"2108.11636","title":"SketchLattice: Latticed Representation for Sketch Manipulation","created":"2021-08-26","cited_by_count":19},{"id":"1510.02644","title":"Free-hand Sketch Synthesis with Deformable Stroke Models","created":"2015-10-09","cited_by_count":16},{"id":"2111.14210","title":"Emergent Graphical Conventions in a Visual Communication Game","created":"2021-11-28","cited_by_count":16},{"id":"2304.10182","title":"Using Text-to-Image Generation for Architectural Design Ideation","created":"2023-04-20","cited_by_count":16},{"id":"2003.07101","title":"Synthesizing human-like sketches from natural images using a conditional convolutional decoder","created":"2020-03-16","cited_by_count":13},{"id":"1903.07820","title":"Trick or TReAT: Thematic Reinforcement for Artistic Typography","created":"2019-03-19","cited_by_count":11},{"id":"1810.05977","title":"Learning to Sketch with Deep Q Networks and Demonstrated Strokes","created":"2018-10-14","cited_by_count":6},{"id":"2106.02775","title":"Visual communication of object concepts at different levels of abstraction","created":"2021-06-05","cited_by_count":5},{"id":"2302.00561","title":"Trash to Treasure: Using text-to-image models to inform the design of physical artefacts","created":"2023-02-01","cited_by_count":3}],"next_cursor":null}