{"list":"other","total":65,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"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":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"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":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"2008.02268","title":"NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections","created":"2020-08-05","cited_by_count":1232},{"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":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"id":"2202.05263","title":"Block-NeRF: Scalable Large Scene Neural View Synthesis","created":"2022-02-10","cited_by_count":724},{"id":"1703.00848","title":"Unsupervised Image-to-Image Translation Networks","created":"2017-03-02","cited_by_count":603},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"2302.03027","title":"Zero-shot Image-to-Image Translation","created":"2023-02-06","cited_by_count":505},{"id":"2312.07920","title":"DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes","created":"2023-12-13","cited_by_count":360},{"id":"2305.16322","title":"Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":359},{"id":"1406.6247","title":"Recurrent Models of Visual Attention","created":"2014-06-24","cited_by_count":349},{"id":"2303.17189","title":"LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation","created":"2023-03-30","cited_by_count":259},{"id":"2305.11147","title":"UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild","created":"2023-05-18","cited_by_count":200},{"id":"2404.01133","title":"CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians","created":"2024-04-01","cited_by_count":192},{"id":"2011.12172","title":"VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval","created":"2020-11-24","cited_by_count":189},{"id":"1510.03743","title":"Wide-Area Image Geolocalization with Aerial Reference Imagery","created":"2015-10-13","cited_by_count":186},{"id":"1903.12351","title":"Lending Orientation to Neural Networks for Cross-view Geo-localization","created":"2019-03-29","cited_by_count":180},{"id":"2205.12952","title":"Pretraining is All You Need for Image-to-Image Translation","created":"2022-05-25","cited_by_count":160},{"id":"1810.12348","title":"Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks","created":"2018-10-29","cited_by_count":139},{"id":"1611.06067","title":"An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data","created":"2016-11-18","cited_by_count":126},{"id":"2005.04551","title":"Epipolar Transformers","created":"2020-05-10","cited_by_count":117},{"id":"2303.00749","title":"S-NeRF: Neural Radiance Fields for Street Views","created":"2023-03-01","cited_by_count":116},{"id":"2103.06818","title":"Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization","created":"2021-03-11","cited_by_count":113},{"id":"1812.10025","title":"Attention Branch Network: Learning of Attention Mechanism for Visual Explanation","created":"2018-12-25","cited_by_count":109},{"id":"1904.06807","title":"Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation","created":"2019-04-15","cited_by_count":97},{"id":"1904.11045","title":"Bridging the Domain Gap for Ground-to-Aerial Image Matching","created":"2019-04-24","cited_by_count":95},{"id":"2203.09283","title":"PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation","created":"2022-03-17","cited_by_count":95},{"id":"2308.05095","title":"LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation","created":"2023-08-09","cited_by_count":92},{"id":"1612.02709","title":"Predicting Ground-Level Scene Layout from Aerial Imagery","created":"2016-12-08","cited_by_count":90},{"id":"1803.03396","title":"Cross-View Image Synthesis using Conditional GANs","created":"2018-03-09","cited_by_count":69},{"id":"2303.14412","title":"Freestyle Layout-to-Image Synthesis","created":"2023-03-25","cited_by_count":67},{"id":"2304.03869","title":"Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis","created":"2023-04-07","cited_by_count":51},{"id":"2203.14148","title":"Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching","created":"2022-03-26","cited_by_count":44},{"id":"2103.01623","title":"Geometry-Guided Street-View Panorama Synthesis from Satellite Imagery","created":"2021-03-02","cited_by_count":41},{"id":"2406.12849","title":"Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentation","created":"2024-06-18","cited_by_count":38},{"id":"1808.05469","title":"Cross-view image synthesis using geometry-guided conditional GANs","created":"2018-08-14","cited_by_count":30},{"id":"2303.14672","title":"Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairs","created":"2023-03-26","cited_by_count":29},{"id":"2203.11832","title":"Cross-View Panorama Image Synthesis","created":"2022-03-22","cited_by_count":26},{"id":"2012.06628","title":"Sat2Vid: Street-view Panoramic Video Synthesis from a Single Satellite Image","created":"2020-12-11","cited_by_count":25},{"id":"1810.04511","title":"Interpretable Spatio-temporal Attention for Video Action Recognition","created":"2018-10-01","cited_by_count":20},{"id":"1708.03035","title":"A Unified Model for Near and Remote Sensing","created":"2017-08-09","cited_by_count":14},{"id":"2204.01807","title":"Revisiting Near/Remote Sensing with Geospatial Attention","created":"2022-04-04","cited_by_count":12},{"id":"2204.08563","title":"Cylin-Painting: Seamless {360\\textdegree} Panoramic Image Outpainting and Beyond","created":"2022-04-18","cited_by_count":12}],"next_cursor":null}