{"list":"other","total":65,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"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":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"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":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"id":"2111.09881","title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","created":"2021-11-18","cited_by_count":1627},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1501.00092","title":"Image Super-Resolution Using Deep Convolutional Networks","created":"2014-12-31","cited_by_count":1224},{"id":"2006.09011","title":"Improved Techniques for Training Score-Based Generative Models","created":"2020-06-16","cited_by_count":1043},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"2106.03106","title":"Uformer: A General U-Shaped Transformer for Image Restoration","created":"2021-06-06","cited_by_count":866},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"1605.05396","title":"Generative Adversarial Text to Image Synthesis","created":"2016-05-17","cited_by_count":735},{"id":"1711.10485","title":"AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks","created":"2017-11-28","cited_by_count":664},{"id":"1612.03242","title":"StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks","created":"2016-12-10","cited_by_count":577},{"id":"1804.07723","title":"Image Inpainting for Irregular Holes Using Partial Convolutions","created":"2018-04-20","cited_by_count":505},{"id":"2112.05139","title":"CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields","created":"2021-12-09","cited_by_count":370},{"id":"2101.04061","title":"Towards Real-World Blind Face Restoration with Generative Facial Prior","created":"2021-01-11","cited_by_count":349},{"id":"2108.05054","title":"Rethinking Coarse-to-Fine Approach in Single Image Deblurring","created":"2021-08-11","cited_by_count":326},{"id":"2003.06792","title":"Learning Enriched Features for Real Image Restoration and Enhancement","created":"2020-03-15","cited_by_count":312},{"id":"2204.14217","title":"CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers","created":"2022-04-28","cited_by_count":307},{"id":"2204.08583","title":"VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance","created":"2022-04-18","cited_by_count":285},{"id":"1903.10082","title":"Residual Non-local Attention Networks for Image Restoration","created":"2019-03-24","cited_by_count":236},{"id":"2206.11253","title":"Towards Robust Blind Face Restoration with Codebook Lookup Transformer","created":"2022-06-22","cited_by_count":231},{"id":"1710.10916","title":"StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks","created":"2017-10-19","cited_by_count":229},{"id":"2112.05744","title":"More Control for Free! Image Synthesis with Semantic Diffusion Guidance","created":"2021-12-10","cited_by_count":212},{"id":"1807.05698","title":"Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining","created":"2018-07-16","cited_by_count":205},{"id":"2112.00374","title":"CLIPstyler: Image Style Transfer with a Single Text Condition","created":"2021-12-01","cited_by_count":203},{"id":"2105.06070","title":"GAN Prior Embedded Network for Blind Face Restoration in the Wild","created":"2021-05-13","cited_by_count":197},{"id":"1711.10703","title":"FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors","created":"2017-11-29","cited_by_count":170},{"id":"2005.00305","title":"Defocus Deblurring Using Dual-Pixel Data","created":"2020-05-01","cited_by_count":139},{"id":"1511.02793","title":"Generating Images from Captions with Attention","created":"2015-11-09","cited_by_count":136},{"id":"2109.04425","title":"Talk-to-Edit: Fine-Grained Facial Editing via Dialog","created":"2021-09-09","cited_by_count":102},{"id":"2104.01431","title":"Aggregated Contextual Transformations for High-Resolution Image Inpainting","created":"2021-04-03","cited_by_count":89},{"id":"2112.05142","title":"HairCLIP: Design Your Hair by Text and Reference Image","created":"2021-12-09","cited_by_count":80},{"id":"2112.05219","title":"CLIP2StyleGAN: Unsupervised Extraction of StyleGAN Edit Directions","created":"2021-12-09","cited_by_count":78},{"id":"1903.08817","title":"Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration","created":"2019-03-21","cited_by_count":73},{"id":"2110.03680","title":"Burst Image Restoration and Enhancement","created":"2021-10-07","cited_by_count":64},{"id":"1711.06288","title":"Language-Based Image Editing with Recurrent Attentive Models","created":"2017-11-16","cited_by_count":53},{"id":"2203.07319","title":"GCFSR: a Generative and Controllable Face Super Resolution Method Without Facial and GAN Priors","created":"2022-03-14","cited_by_count":39},{"id":"2202.05009","title":"N\\\"UWA-LIP: Language Guided Image Inpainting with Defect-free VQGAN","created":"2022-02-10","cited_by_count":19},{"id":"2209.03300","title":"Spach Transformer: Spatial and Channel-wise Transformer Based on Local and Global Self-attentions for PET Image Denoising","created":"2022-09-07","cited_by_count":19},{"id":"2004.04433","title":"DeepSEE: Deep Disentangled Semantic Explorative Extreme Super-Resolution","created":"2020-04-09","cited_by_count":17},{"id":"2112.01335","title":"Semantic-Sparse Colorization Network for Deep Exemplar-based Colorization","created":"2021-12-02","cited_by_count":12}],"next_cursor":null}