{"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":"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"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":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"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":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"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":"1912.02762","title":"Normalizing Flows for Probabilistic Modeling and Inference","created":"2019-12-05","cited_by_count":1323},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738},{"id":"1504.06375","title":"Holistically-Nested Edge Detection","created":"2015-04-24","cited_by_count":592},{"id":"1610.09585","title":"Conditional Image Synthesis With Auxiliary Classifier GANs","created":"2016-10-30","cited_by_count":565},{"id":"2203.13131","title":"Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors","created":"2022-03-24","cited_by_count":487},{"id":"1905.12681","title":"What Makes Training Multi-Modal Classification Networks Hard?","created":"2019-05-29","cited_by_count":344},{"id":"2302.09778","title":"Composer: Creative and Controllable Image Synthesis with Composable Conditions","created":"2023-02-20","cited_by_count":304},{"id":"2203.15332","title":"Balanced Multimodal Learning via On-the-fly Gradient Modulation","created":"2022-03-29","cited_by_count":264},{"id":"1802.05637","title":"cGANs with Projection Discriminator","created":"2018-02-15","cited_by_count":254},{"id":"2111.12417","title":"N\\\"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion","created":"2021-11-24","cited_by_count":253},{"id":"2103.04922","title":"Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models","created":"2021-03-08","cited_by_count":252},{"id":"2204.05454","title":"Are Multimodal Transformers Robust to Missing Modality?","created":"2022-04-12","cited_by_count":186},{"id":"2205.12952","title":"Pretraining is All You Need for Image-to-Image Translation","created":"2022-05-25","cited_by_count":160},{"id":"2106.04538","title":"What Makes Multi-modal Learning Better than Single (Provably)","created":"2021-06-08","cited_by_count":153},{"id":"2203.12221","title":"Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)","created":"2022-03-23","cited_by_count":122},{"id":"1910.06809","title":"Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis","created":"2019-10-15","cited_by_count":108},{"id":"1911.09267","title":"Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis","created":"2019-11-21","cited_by_count":106},{"id":"2112.05130","title":"Multimodal Conditional Image Synthesis with Product-of-Experts GANs","created":"2021-12-09","cited_by_count":75},{"id":"2207.09814","title":"NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis","created":"2022-07-20","cited_by_count":71},{"id":"2104.06954","title":"Aligning Latent and Image Spaces to Connect the Unconnectable","created":"2021-04-14","cited_by_count":70},{"id":"2107.02423","title":"Improving Text-to-Image Synthesis Using Contrastive Learning","created":"2021-07-06","cited_by_count":62},{"id":"2003.07449","title":"Object-Centric Image Generation from Layouts","created":"2020-03-16","cited_by_count":57},{"id":"2104.11222","title":"On Aliased Resizing and Surprising Subtleties in GAN Evaluation","created":"2021-04-22","cited_by_count":51},{"id":"2003.11571","title":"Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis","created":"2020-03-25","cited_by_count":49},{"id":"2206.00923","title":"Modeling Image Composition for Complex Scene Generation","created":"2022-06-02","cited_by_count":43},{"id":"2103.11897","title":"Context-Aware Layout to Image Generation with Enhanced Object Appearance","created":"2021-03-22","cited_by_count":41},{"id":"2105.06458","title":"High-Resolution Complex Scene Synthesis with Transformers","created":"2021-05-13","cited_by_count":31},{"id":"2205.11705","title":"M6-Fashion: High-Fidelity Multi-modal Image Generation and Editing","created":"2022-05-24","cited_by_count":3}],"next_cursor":null}