{"list":"other","total":52,"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"1701.04128","title":"Understanding the Effective Receptive Field in Deep Convolutional Neural Networks","created":"2017-01-15","cited_by_count":553},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"id":"1508.06576","title":"A Neural Algorithm of Artistic Style","created":"2015-08-26","cited_by_count":483},{"id":"2401.04722","title":"U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation","created":"2024-01-09","cited_by_count":419},{"id":"2402.15648","title":"MambaIR: A Simple Baseline for Image Restoration with State-Space Model","created":"2024-02-23","cited_by_count":352},{"id":"1610.07629","title":"A Learned Representation For Artistic Style","created":"2016-10-24","cited_by_count":341},{"id":"2206.13947","title":"Long Range Language Modeling via Gated State Spaces","created":"2022-06-27","cited_by_count":265},{"id":"2312.09008","title":"Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer","created":"2023-12-11","cited_by_count":196},{"id":"2105.14576","title":"StyTr$^2$: Image Style Transfer with Transformers","created":"2021-05-30","cited_by_count":187},{"id":"2104.00416","title":"Unsupervised Degradation Representation Learning for Blind Super-Resolution","created":"2021-04-01","cited_by_count":177},{"id":"1603.03417","title":"Texture Networks: Feed-forward Synthesis of Textures and Stylized Images","created":"2016-03-10","cited_by_count":174},{"id":"2209.15264","title":"Diffusion-based Image Translation using Disentangled Style and Content Representation","created":"2022-09-30","cited_by_count":149},{"id":"2203.07740","title":"Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization","created":"2022-03-15","cited_by_count":122},{"id":"2103.16877","title":"ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows","created":"2021-03-31","cited_by_count":113},{"id":"2303.14526","title":"Selective Structured State-Spaces for Long-Form Video Understanding","created":"2023-03-25","cited_by_count":105},{"id":"2403.11423","title":"VmambaIR: Visual State Space Model for Image Restoration","created":"2024-03-18","cited_by_count":90},{"id":"1703.09210","title":"StyleBank: An Explicit Representation for Neural Image Style Transfer","created":"2017-03-27","cited_by_count":89},{"id":"2009.08003","title":"Arbitrary Video Style Transfer via Multi-Channel Correlation","created":"2020-09-17","cited_by_count":84},{"id":"2403.13802","title":"ZigMa: A DiT-style Zigzag Mamba Diffusion Model","created":"2024-03-20","cited_by_count":84},{"id":"1911.06953","title":"Dynamic Instance Normalization for Arbitrary Style Transfer","created":"2019-11-16","cited_by_count":83},{"id":"2404.09498","title":"FusionMamba: Dynamic Feature Enhancement for Multimodal Image Fusion with Mamba","created":"2024-04-15","cited_by_count":81},{"id":"1703.06953","title":"Multi-style Generative Network for Real-time Transfer","created":"2017-03-20","cited_by_count":61},{"id":"2212.14427","title":"Efficient Movie Scene Detection using State-Space Transformers","created":"2022-12-29","cited_by_count":51},{"id":"2207.12280","title":"ArtFID: Quantitative Evaluation of Neural Style Transfer","created":"2022-07-25","cited_by_count":49},{"id":"2307.09724","title":"AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networks","created":"2023-07-19","cited_by_count":34},{"id":"2307.14352","title":"General Image-to-Image Translation with One-Shot Image Guidance","created":"2023-07-20","cited_by_count":31},{"id":"2303.17867","title":"CAP-VSTNet: Content Affinity Preserved Versatile Style Transfer","created":"2023-03-31","cited_by_count":24},{"id":"2405.08493","title":"Rethinking Scanning Strategies with Vision Mamba in Semantic Segmentation of Remote Sensing Imagery: An Experimental Study","created":"2024-05-14","cited_by_count":24},{"id":"2211.15313","title":"MicroAST: Towards Super-Fast Ultra-Resolution Arbitrary Style Transfer","created":"2022-11-28","cited_by_count":19},{"id":"2212.04105","title":"All-to-key Attention for Arbitrary Style Transfer","created":"2022-12-08","cited_by_count":16},{"id":"2210.12381","title":"S2WAT: Image Style Transfer via Hierarchical Vision Transformer using Strips Window Attention","created":"2022-10-22","cited_by_count":14},{"id":"2210.05176","title":"Fine-Grained Image Style Transfer with Visual Transformers","created":"2022-10-11","cited_by_count":11},{"id":"2303.12710","title":"A Unified Arbitrary Style Transfer Framework via Adaptive Contrastive Learning","created":"2023-03-09","cited_by_count":10},{"id":"2405.19775","title":"Puff-Net: Efficient Style Transfer with Pure Content and Style Feature Fusion Network","created":"2024-05-30","cited_by_count":5}],"next_cursor":null}