{"list":"other","total":112,"rows":[{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"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":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"id":"1506.03365","title":"LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop","created":"2015-06-10","cited_by_count":1355},{"id":"2009.09761","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","created":"2020-09-21","cited_by_count":1354},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"1612.03928","title":"Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer","created":"2016-12-12","cited_by_count":1077},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2205.14217","title":"Diffusion-LM Improves Controllable Text Generation","created":"2022-05-27","cited_by_count":1027},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"1906.02691","title":"An Introduction to Variational Autoencoders","created":"2019-06-06","cited_by_count":1000},{"id":"2209.15571","title":"Building Normalizing Flows with Stochastic Interpolants","created":"2022-09-30","cited_by_count":995},{"id":"2211.12572","title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","created":"2022-11-22","cited_by_count":906},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"2203.17003","title":"Equivariant Diffusion for Molecule Generation in 3D","created":"2022-03-31","cited_by_count":677},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"2009.00713","title":"WaveGrad: Estimating Gradients for Waveform Generation","created":"2020-09-02","cited_by_count":622},{"id":"2102.05379","title":"Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions","created":"2021-02-10","cited_by_count":574},{"id":"1412.7062","title":"Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs","created":"2014-12-22","cited_by_count":554},{"id":"2302.08113","title":"MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation","created":"2023-02-16","cited_by_count":536},{"id":"1911.05371","title":"Self-labelling via simultaneous clustering and representation learning","created":"2019-11-13","cited_by_count":528},{"id":"2112.03126","title":"Label-Efficient Semantic Segmentation with Diffusion Models","created":"2021-12-06","cited_by_count":499},{"id":"2310.01889","title":"Ring Attention with Blockwise Transformers for Near-Infinite Context","created":"2023-10-03","cited_by_count":457},{"id":"2306.03881","title":"Emergent Correspondence from Image Diffusion","created":"2023-06-06","cited_by_count":446},{"id":"2307.10373","title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","created":"2023-07-19","cited_by_count":442},{"id":"2306.15687","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","created":"2023-06-23","cited_by_count":379},{"id":"2303.04803","title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models","created":"2023-03-08","cited_by_count":375},{"id":"1604.05144","title":"ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation","created":"2016-04-18","cited_by_count":331},{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328},{"id":"2301.12661","title":"Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models","created":"2023-01-30","cited_by_count":324},{"id":"1803.10464","title":"Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation","created":"2018-03-28","cited_by_count":321},{"id":"2303.16203","title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","created":"2023-03-28","cited_by_count":306},{"id":"2306.00986","title":"Diffusion Self-Guidance for Controllable Image Generation","created":"2023-06-01","cited_by_count":305},{"id":"2305.15347","title":"A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence","created":"2023-05-24","cited_by_count":301},{"id":"2002.03754","title":"Unsupervised Discovery of Interpretable Directions in the GAN Latent Space","created":"2020-02-10","cited_by_count":289},{"id":"2303.02153","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception","created":"2023-03-03","cited_by_count":269},{"id":"2206.13947","title":"Long Range Language Modeling via Gated State Spaces","created":"2022-06-27","cited_by_count":265},{"id":"1907.02544","title":"Large Scale Adversarial Representation Learning","created":"2019-07-04","cited_by_count":239},{"id":"2211.09117","title":"MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis","created":"2022-11-16","cited_by_count":227},{"id":"2305.04391","title":"A Variational Perspective on Solving Inverse Problems with Diffusion Models","created":"2023-05-07","cited_by_count":222},{"id":"2305.14334","title":"Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence","created":"2023-05-23","cited_by_count":214},{"id":"2402.17525","title":"Diffusion Model-Based Image Editing: A Survey","created":"2024-02-27","cited_by_count":212},{"id":"2311.16863","title":"Power Hungry Processing: Watts Driving the Cost of AI Deployment?","created":"2023-11-28","cited_by_count":191},{"id":"2309.03895","title":"InstructDiffusion: A Generalist Modeling Interface for Vision Tasks","created":"2023-09-07","cited_by_count":164},{"id":"2307.08698","title":"Flow Matching in Latent Space","created":"2023-07-17","cited_by_count":160},{"id":"2105.02446","title":"DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism","created":"2021-05-06","cited_by_count":154},{"id":"1908.10543","title":"SPair-71k: A Large-scale Benchmark for Semantic Correspondence","created":"2019-08-28","cited_by_count":146},{"id":"2204.02849","title":"KNN-Diffusion: Image Generation via Large-Scale Retrieval","created":"2022-04-06","cited_by_count":137},{"id":"2311.17009","title":"Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer","created":"2023-11-28","cited_by_count":124},{"id":"2402.14017","title":"D-Flow: Differentiating through Flows for Controlled Generation","created":"2024-02-21","cited_by_count":122},{"id":"2109.05070","title":"Instance-Conditioned GAN","created":"2021-09-10","cited_by_count":121},{"id":"2305.15581","title":"Unsupervised Semantic Correspondence Using Stable Diffusion","created":"2023-05-24","cited_by_count":120},{"id":"1305.6663","title":"Generalized Denoising Auto-Encoders as Generative Models","created":"2013-05-29","cited_by_count":113},{"id":"2403.09626","title":"Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding","created":"2024-03-14","cited_by_count":108},{"id":"2312.03701","title":"Return of Unconditional Generation: A Self-supervised Representation Generation Method","created":"2023-12-06","cited_by_count":98},{"id":"2311.17034","title":"Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence","created":"2023-11-28","cited_by_count":86},{"id":"2403.13802","title":"ZigMa: A DiT-style Zigzag Mamba Diffusion Model","created":"2024-03-20","cited_by_count":84},{"id":"2302.03298","title":"Diversity is Definitely Needed: Improving Model-Agnostic Zero-shot Classification via Stable Diffusion","created":"2023-02-07","cited_by_count":81},{"id":"2304.14530","title":"Generating images of rare concepts using pre-trained diffusion models","created":"2023-04-27","cited_by_count":79},{"id":"2403.13788","title":"DepthFM: Fast Monocular Depth Estimation with Flow Matching","created":"2024-03-20","cited_by_count":76},{"id":"2312.02190","title":"Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D","created":"2023-12-02","cited_by_count":59},{"id":"1511.05065","title":"Proposal Flow","created":"2015-11-16","cited_by_count":57},{"id":"2105.14257","title":"Diffusion-Based Representation Learning","created":"2021-05-29","cited_by_count":57},{"id":"2006.10728","title":"Diverse Image Generation via Self-Conditioned GANs","created":"2020-06-18","cited_by_count":55},{"id":"2211.14575","title":"Efficient Video Prediction via Sparsely Conditioned Flow Matching","created":"2022-11-26","cited_by_count":55},{"id":"2312.02150","title":"Readout Guidance: Learning Control from Diffusion Features","created":"2023-12-04","cited_by_count":52},{"id":"2310.17569","title":"SD4Match: Learning to Prompt Stable Diffusion Model for Semantic Matching","created":"2023-10-26","cited_by_count":38},{"id":"2312.08895","title":"Motion Flow Matching for Human Motion Synthesis and Editing","created":"2023-12-14","cited_by_count":38}],"next_cursor":"100"}