{"list":"other","total":53,"rows":[{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"id":"1904.06991","title":"Improved Precision and Recall Metric for Assessing Generative Models","created":"2019-04-15","cited_by_count":944},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"1810.01367","title":"FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models","created":"2018-10-02","cited_by_count":594},{"id":"2105.06337","title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","created":"2021-05-13","cited_by_count":447},{"id":"2002.09797","title":"Reliable Fidelity and Diversity Metrics for Generative Models","created":"2020-02-23","cited_by_count":434},{"id":"2303.16203","title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","created":"2023-03-28","cited_by_count":306},{"id":"1611.07828","title":"Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose","created":"2016-11-23","cited_by_count":221},{"id":"2112.03145","title":"Diffusion Models for Implicit Image Segmentation Ensembles","created":"2021-12-06","cited_by_count":198},{"id":"2103.16483","title":"Benchmarking Representation Learning for Natural World Image Collections","created":"2021-03-30","cited_by_count":168},{"id":"2103.16091","title":"Symbolic Music Generation with Diffusion Models","created":"2021-03-30","cited_by_count":154},{"id":"1509.05909","title":"Modelling Uncertainty in Deep Learning for Camera Relocalization","created":"2015-09-19","cited_by_count":134},{"id":"1406.2984","title":"Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation","created":"2014-06-11","cited_by_count":129},{"id":"1602.05314","title":"PlaNet - Photo Geolocation with Convolutional Neural Networks","created":"2016-02-17","cited_by_count":115},{"id":"2401.08559","title":"Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation","created":"2024-01-16","cited_by_count":91},{"id":"1705.04838","title":"Revisiting IM2GPS in the Deep Learning Era","created":"2017-05-13","cited_by_count":80},{"id":"1808.02130","title":"CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps","created":"2018-08-06","cited_by_count":68},{"id":"2204.13861","title":"Where in the World is this Image? Transformer-based Geo-localization in the Wild","created":"2022-04-29","cited_by_count":58},{"id":"2207.04711","title":"Matching Normalizing Flows and Probability Paths on Manifolds","created":"2022-07-11","cited_by_count":57},{"id":"2307.05845","title":"PIGEON: Predicting Image Geolocations","created":"2023-07-11","cited_by_count":56},{"id":"2303.04249","title":"Where We Are and What We're Looking At: Query Based Worldwide Image Geo-localization Using Hierarchies and Scenes","created":"2023-03-07","cited_by_count":55},{"id":"2012.11002","title":"Deep Bingham Networks: Dealing with Uncertainty and Ambiguity in Pose Estimation","created":"2020-12-20","cited_by_count":43},{"id":"2302.00275","title":"Learning Generalized Zero-Shot Learners for Open-Domain Image Geolocalization","created":"2023-02-01","cited_by_count":41},{"id":"2404.18873","title":"OpenStreetView-5M: The Many Roads to Global Visual Geolocation","created":"2024-04-29","cited_by_count":38},{"id":"2104.14995","title":"Interpretable Semantic Photo Geolocation","created":"2021-04-30","cited_by_count":32},{"id":"2205.01823","title":"Symmetry and Uncertainty-Aware Object SLAM for 6DoF Object Pose Estimation","created":"2022-05-04","cited_by_count":28},{"id":"2407.01516","title":"E.T. the Exceptional Trajectories: Text-to-camera-trajectory generation with character awareness","created":"2024-07-01","cited_by_count":25},{"id":"2401.00029","title":"6D-Diff: A Keypoint Diffusion Framework for 6D Object Pose Estimation","created":"2023-12-29","cited_by_count":24},{"id":"2406.18580","title":"Shedding Light on Large Generative Networks: Estimating Epistemic Uncertainty in Diffusion Models","created":"2024-06-05","cited_by_count":22},{"id":"2203.08504","title":"A Survey of Historical Document Image Datasets","created":"2022-03-16","cited_by_count":20},{"id":"2105.07645","title":"Leveraging EfficientNet and Contrastive Learning for Accurate Global-scale Location Estimation","created":"2021-05-17","cited_by_count":19},{"id":"2405.20324","title":"Don't drop your samples! Coherence-aware training benefits Conditional diffusion","created":"2024-05-30","cited_by_count":13},{"id":"2301.02086","title":"A Probabilistic Framework for Visual Localization in Ambiguous Scenes","created":"2023-01-05","cited_by_count":12},{"id":"2210.04883","title":"SCAM! Transferring humans between images with Semantic Cross Attention Modulation","created":"2022-10-10","cited_by_count":10},{"id":"1409.1461","title":"On the Accuracy of Hyper-local Geotagging of Social Media Content","created":"2014-09-04","cited_by_count":3},{"id":"2304.08841","title":"Two-stage Denoising Diffusion Model for Source Localization in Graph Inverse Problems","created":"2023-04-18","cited_by_count":3},{"id":"2402.15448","title":"Computer Vision for Multimedia Geolocation in Human Trafficking Investigation: A Systematic Literature Review","created":"2024-02-23","cited_by_count":3}],"next_cursor":null}