{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651},{"id":"2110.02711","title":"DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation","created":"2021-10-06","cited_by_count":642},{"id":"1705.08086","title":"Universal Style Transfer via Feature Transforms","created":"2017-05-23","cited_by_count":354},{"id":"2211.13203","title":"Inversion-Based Style Transfer with Diffusion Models","created":"2022-11-23","cited_by_count":291},{"id":"2002.06353","title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation","created":"2020-02-15","cited_by_count":259},{"id":"2106.11097","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","created":"2021-06-21","cited_by_count":225},{"id":"2112.05744","title":"More Control for Free! Image Synthesis with Semantic Diffusion Guidance","created":"2021-12-10","cited_by_count":212},{"id":"2112.00374","title":"CLIPstyler: Image Style Transfer with a Single Text Condition","created":"2021-12-01","cited_by_count":203},{"id":"1812.02342","title":"Arbitrary Style Transfer with Style-Attentional Networks","created":"2018-12-06","cited_by_count":198},{"id":"2105.14576","title":"StyTr$^2$: Image Style Transfer with Transformers","created":"2021-05-30","cited_by_count":187},{"id":"2106.14843","title":"CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders","created":"2021-06-28","cited_by_count":187},{"id":"2108.03647","title":"AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer","created":"2021-08-08","cited_by_count":178},{"id":"1603.03417","title":"Texture Networks: Feed-forward Synthesis of Textures and Stylized Images","created":"2016-03-10","cited_by_count":174},{"id":"1904.12785","title":"Style Transfer by Relaxed Optimal Transport and Self-Similarity","created":"2019-04-29","cited_by_count":168},{"id":"2308.07863","title":"StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models","created":"2023-08-15","cited_by_count":155},{"id":"1805.03857","title":"Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration","created":"2018-05-10","cited_by_count":115},{"id":"2103.16877","title":"ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows","created":"2021-03-31","cited_by_count":113},{"id":"2205.09542","title":"Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning","created":"2022-05-19","cited_by_count":93},{"id":"2303.08622","title":"Zero-Shot Contrastive Loss for Text-Guided Diffusion Image Style Transfer","created":"2023-03-15","cited_by_count":59},{"id":"1807.10201","title":"A Style-Aware Content Loss for Real-time HD Style Transfer","created":"2018-07-26","cited_by_count":58},{"id":"2110.00351","title":"Smooth Normalizing Flows","created":"2021-10-01","cited_by_count":53},{"id":"1808.04537","title":"Learning Linear Transformations for Fast Arbitrary Style Transfer","created":"2018-08-14","cited_by_count":48},{"id":"2211.10682","title":"DiffStyler: Controllable Dual Diffusion for Text-Driven Image Stylization","created":"2022-11-19","cited_by_count":45},{"id":"1704.04517","title":"ShapeWorld - A new test methodology for multimodal language understanding","created":"2017-04-14","cited_by_count":37},{"id":"2106.00178","title":"Language-Driven Image Style Transfer","created":"2021-06-01","cited_by_count":37},{"id":"2209.13360","title":"Draw Your Art Dream: Diverse Digital Art Synthesis with Multimodal Guided Diffusion","created":"2022-09-27","cited_by_count":30},{"id":"1907.06370","title":"Multimodal deep networks for text and image-based document classification","created":"2019-07-15","cited_by_count":24},{"id":"2108.08688","title":"Contrastive Language-Image Pre-training for the Italian Language","created":"2021-08-19","cited_by_count":19},{"id":"2212.10431","title":"QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity","created":"2022-12-20","cited_by_count":18},{"id":"2208.05621","title":"ARMANI: Part-level Garment-Text Alignment for Unified Cross-Modal Fashion Design","created":"2022-08-11","cited_by_count":16},{"id":"2212.04105","title":"All-to-key Attention for Arbitrary Style Transfer","created":"2022-12-08","cited_by_count":16},{"id":"2110.04292","title":"Toward a Visual Concept Vocabulary for GAN Latent Space","created":"2021-10-08","cited_by_count":15},{"id":"2111.03133","title":"StyleCLIPDraw: Coupling Content and Style in Text-to-Drawing Synthesis","created":"2021-11-04","cited_by_count":15},{"id":"2202.13562","title":"Name Your Style: An Arbitrary Artist-aware Image Style Transfer","created":"2022-02-28","cited_by_count":14},{"id":"2304.00414","title":"Learning Dynamic Style Kernels for Artistic Style Transfer","created":"2023-04-02","cited_by_count":12},{"id":"2210.05176","title":"Fine-Grained Image Style Transfer with Visual Transformers","created":"2022-10-11","cited_by_count":11},{"id":"2210.04883","title":"SCAM! Transferring humans between images with Semantic Cross Attention Modulation","created":"2022-10-10","cited_by_count":10},{"id":"2303.09268","title":"StylerDALLE: Language-Guided Style Transfer Using a Vector-Quantized Tokenizer of a Large-Scale Generative Model","created":"2023-03-16","cited_by_count":10},{"id":"2110.07375","title":"Multiple Style Transfer via Variational AutoEncoder","created":"2021-10-13","cited_by_count":9},{"id":"2208.14889","title":"LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data","created":"2022-08-31","cited_by_count":5}],"next_cursor":null}