{"list":"other","total":78,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"2006.09661","title":"Implicit Neural Representations with Periodic Activation Functions","created":"2020-06-17","cited_by_count":2238},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"1705.08045","title":"Learning multiple visual domains with residual adapters","created":"2017-05-22","cited_by_count":557},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"1805.01934","title":"Learning to See in the Dark","created":"2018-05-04","cited_by_count":460},{"id":"2306.01567","title":"Segment Anything in High Quality","created":"2023-06-02","cited_by_count":376},{"id":"2207.09519","title":"Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification","created":"2022-07-19","cited_by_count":362},{"id":"2111.13679","title":"NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images","created":"2021-11-26","cited_by_count":336},{"id":"2112.06825","title":"VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks","created":"2021-12-13","cited_by_count":320},{"id":"1811.11127","title":"Unprocessing Images for Learned Raw Denoising","created":"2018-11-27","cited_by_count":250},{"id":"2111.14813","title":"TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions","created":"2021-11-29","cited_by_count":244},{"id":"2003.07761","title":"CycleISP: Real Image Restoration via Improved Data Synthesis","created":"2020-03-17","cited_by_count":213},{"id":"2201.00299","title":"Improving Out-of-Distribution Robustness via Selective Augmentation","created":"2022-01-02","cited_by_count":202},{"id":"2111.05328","title":"Data Augmentation Can Improve Robustness","created":"2021-11-09","cited_by_count":194},{"id":"2003.12751","title":"A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising","created":"2020-03-28","cited_by_count":138},{"id":"1711.09856","title":"On the Robustness of Semantic Segmentation Models to Adversarial Attacks","created":"2017-11-27","cited_by_count":126},{"id":"2203.01441","title":"3D Common Corruptions and Data Augmentation","created":"2022-03-02","cited_by_count":119},{"id":"1908.05005","title":"Benchmarking the Robustness of Semantic Segmentation Models","created":"2019-08-14","cited_by_count":111},{"id":"2002.05509","title":"Replacing Mobile Camera ISP with a Single Deep Learning Model","created":"2020-02-13","cited_by_count":108},{"id":"2004.00713","title":"Memory-Efficient Incremental Learning Through Feature Adaptation","created":"2020-04-01","cited_by_count":107},{"id":"2103.15061","title":"Invertible Image Signal Processing","created":"2021-03-28","cited_by_count":94},{"id":"1801.06724","title":"DeepISP: Towards Learning an End-to-End Image Processing Pipeline","created":"2018-01-20","cited_by_count":88},{"id":"2205.14871","title":"You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction","created":"2022-05-30","cited_by_count":81},{"id":"2102.09000","title":"Mobile Computational Photography: A Tour","created":"2021-02-17","cited_by_count":62},{"id":"2205.03346","title":"Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection","created":"2022-05-06","cited_by_count":59},{"id":"2403.01439","title":"Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis","created":"2024-03-03","cited_by_count":53},{"id":"2011.12485","title":"How to Train Neural Networks for Flare Removal","created":"2020-11-25","cited_by_count":50},{"id":"2210.06570","title":"Flare7K: A Phenomenological Nighttime Flare Removal Dataset","created":"2022-10-12","cited_by_count":49},{"id":"2204.04210","title":"Dancing under the stars: video denoising in starlight","created":"2022-04-08","cited_by_count":47},{"id":"2304.14298","title":"Instance Segmentation in the Dark","created":"2023-04-27","cited_by_count":46},{"id":"2108.08119","title":"Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision","created":"2021-08-18","cited_by_count":43},{"id":"2201.03210","title":"Model-Based Image Signal Processors via Learnable Dictionaries","created":"2022-01-10","cited_by_count":43},{"id":"1701.06487","title":"Dirty Pixels: Towards End-to-End Image Processing and Perception","created":"2017-01-23","cited_by_count":42},{"id":"1908.01481","title":"CameraNet: A Two-Stage Framework for Effective Camera ISP Learning","created":"2019-08-05","cited_by_count":38},{"id":"1912.06960","title":"What Else Can Fool Deep Learning? Addressing Color Constancy Errors on Deep Neural Network Performance","created":"2019-12-15","cited_by_count":37},{"id":"2404.04804","title":"Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous Driving","created":"2024-04-07","cited_by_count":35},{"id":"1705.04352","title":"Reconfiguring the Imaging Pipeline for Computer Vision","created":"2017-05-11","cited_by_count":32},{"id":"2306.04236","title":"Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyond","created":"2023-06-07","cited_by_count":31},{"id":"2306.11920","title":"NILUT: Conditional Neural Implicit 3D Lookup Tables for Image Enhancement","created":"2023-06-20","cited_by_count":31},{"id":"2109.04760","title":"ReconfigISP: Reconfigurable Camera Image Processing Pipeline","created":"2021-09-10","cited_by_count":30},{"id":"2406.06216","title":"Lighting Every Darkness with 3DGS: Fast Training and Real-Time Rendering for HDR View Synthesis","created":"2024-06-10","cited_by_count":27},{"id":"2211.01146","title":"DynamicISP: Dynamically Controlled Image Signal Processor for Image Recognition","created":"2022-11-02","cited_by_count":23},{"id":"2312.13313","title":"ParamISP: Learned Forward and Inverse ISPs using Camera Parameters","created":"2023-12-20","cited_by_count":23},{"id":"1902.09023","title":"Automatic ISP image quality tuning using non-linear optimization","created":"2019-02-24","cited_by_count":20},{"id":"2408.14802","title":"RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images","created":"2024-08-27","cited_by_count":19},{"id":"1911.05931","title":"VisionISP: Repurposing the Image Signal Processor for Computer Vision Applications","created":"2019-11-14","cited_by_count":18},{"id":"2011.14448","title":"Improved Handling of Motion Blur in Online Object Detection","created":"2020-11-29","cited_by_count":18},{"id":"2210.16046","title":"Rawgment: Noise-Accounted RAW Augmentation Enables Recognition in a Wide Variety of Environments","created":"2022-10-28","cited_by_count":18},{"id":"2212.07778","title":"Efficient Visual Computing with Camera RAW Snapshots","created":"2022-12-15","cited_by_count":18},{"id":"2302.12995","title":"Raw Image Reconstruction with Learned Compact Metadata","created":"2023-02-25","cited_by_count":18},{"id":"2410.22939","title":"AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection","created":"2024-10-30","cited_by_count":18},{"id":"2106.13883","title":"Semi-Supervised Raw-to-Raw Mapping","created":"2021-06-25","cited_by_count":16},{"id":"2401.02161","title":"Enhancing RAW-to-sRGB with Decoupled Style Structure in Fourier Domain","created":"2024-01-04","cited_by_count":14},{"id":"2310.20332","title":"Recaptured Raw Screen Image and Video Demoir\\'eing via Channel and Spatial Modulations","created":"2023-10-31","cited_by_count":12},{"id":"2307.00761","title":"Learning Degradation-Independent Representations for Camera ISP Pipelines","created":"2023-07-03","cited_by_count":11},{"id":"2404.10700","title":"Rawformer: Unpaired Raw-to-Raw Translation for Learnable Camera ISPs","created":"2024-04-16","cited_by_count":11},{"id":"2409.18783","title":"DualDn: Dual-domain Denoising via Differentiable ISP","created":"2024-09-27","cited_by_count":11},{"id":"2411.15678","title":"Towards RAW Object Detection in Diverse Conditions","created":"2024-11-24","cited_by_count":9},{"id":"1707.08350","title":"Modelling the Scene Dependent Imaging in Cameras with a Deep Neural Network","created":"2017-07-26","cited_by_count":8},{"id":"2410.14214","title":"MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging","created":"2024-10-18","cited_by_count":7},{"id":"2208.03062","title":"Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection","created":"2022-08-05","cited_by_count":6},{"id":"2401.03220","title":"MetaISP -- Exploiting Global Scene Structure for Accurate Multi-Device Color Rendition","created":"2024-01-06","cited_by_count":5}],"next_cursor":null}