{"list":"other","total":76,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"id":"2111.09881","title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","created":"2021-11-18","cited_by_count":1627},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"id":"2106.03106","title":"Uformer: A General U-Shaped Transformer for Image Restoration","created":"2021-06-06","cited_by_count":866},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2102.02808","title":"Multi-Stage Progressive Image Restoration","created":"2021-02-04","cited_by_count":816},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532},{"id":"2112.10003","title":"Image Segmentation Using Text and Image Prompts","created":"2021-12-18","cited_by_count":512},{"id":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484},{"id":"1312.6184","title":"Do Deep Nets Really Need to be Deep?","created":"2013-12-21","cited_by_count":474},{"id":"2111.15174","title":"CRIS: CLIP-Driven Referring Image Segmentation","created":"2021-11-30","cited_by_count":353},{"id":"1605.09673","title":"Dynamic Filter Networks","created":"2016-05-31","cited_by_count":319},{"id":"1601.07661","title":"DehazeNet: An End-to-End System for Single Image Haze Removal","created":"2016-01-28","cited_by_count":314},{"id":"2003.05664","title":"Conditional Convolutions for Instance Segmentation","created":"2020-03-12","cited_by_count":314},{"id":"1903.04197","title":"Structured Knowledge Distillation for Dense Prediction","created":"2019-03-11","cited_by_count":279},{"id":"1904.04971","title":"CondConv: Conditionally Parameterized Convolutions for Efficient Inference","created":"2019-04-10","cited_by_count":273},{"id":"2111.14813","title":"TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions","created":"2021-11-29","cited_by_count":244},{"id":"2004.13388","title":"Multi-Scale Boosted Dehazing Network with Dense Feature Fusion","created":"2020-04-28","cited_by_count":230},{"id":"2104.05707","title":"LocalViT: Analyzing Locality in Vision Transformers","created":"2021-04-12","cited_by_count":228},{"id":"1908.03245","title":"GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing","created":"2019-08-08","cited_by_count":227},{"id":"2104.09367","title":"Contrastive Learning for Compact Single Image Dehazing","created":"2021-04-19","cited_by_count":219},{"id":"2207.14626","title":"Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models","created":"2022-07-29","cited_by_count":215},{"id":"2205.10536","title":"Knowledge Distillation from A Stronger Teacher","created":"2022-05-21","cited_by_count":208},{"id":"1711.10098","title":"Attentive Generative Adversarial Network for Raindrop Removal from a Single Image","created":"2017-11-28","cited_by_count":204},{"id":"2206.02770","title":"Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts","created":"2022-06-06","cited_by_count":203},{"id":"1708.04512","title":"DesnowNet: Context-Aware Deep Network for Snow Removal","created":"2017-08-15","cited_by_count":200},{"id":"1904.01538","title":"Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset","created":"2019-04-02","cited_by_count":192},{"id":"1906.03609","title":"Distilling Object Detectors with Fine-grained Feature Imitation","created":"2019-06-09","cited_by_count":189},{"id":"1903.00875","title":"Meta-SR: A Magnification-Arbitrary Network for Super-Resolution","created":"2019-03-03","cited_by_count":181},{"id":"1904.05050","title":"Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning","created":"2019-04-10","cited_by_count":157},{"id":"1803.08396","title":"Densely Connected Pyramid Dehazing Network","created":"2018-03-22","cited_by_count":145},{"id":"2005.01333","title":"A Model-driven Deep Neural Network for Single Image Rain Removal","created":"2020-05-04","cited_by_count":125},{"id":"1910.06809","title":"Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis","created":"2019-10-15","cited_by_count":108},{"id":"2112.08088","title":"Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions","created":"2021-12-15","cited_by_count":85},{"id":"2103.11298","title":"Deep Dense Multi-scale Network for Snow Removal Using Semantic and Geometric Priors","created":"2021-03-21","cited_by_count":82},{"id":"2112.05142","title":"HairCLIP: Design Your Hair by Text and Reference Image","created":"2021-12-09","cited_by_count":80},{"id":"1905.09797","title":"Interpreting Adversarially Trained Convolutional Neural Networks","created":"2019-05-23","cited_by_count":75},{"id":"1903.08817","title":"Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration","created":"2019-03-21","cited_by_count":73},{"id":"2004.00448","title":"Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy","created":"2020-04-01","cited_by_count":66},{"id":"2004.06965","title":"Unified Dynamic Convolutional Network for Super-Resolution with Variational Degradations","created":"2020-04-15","cited_by_count":61},{"id":"2003.12243","title":"Dynamic Region-Aware Convolution","created":"2020-03-27","cited_by_count":50},{"id":"2109.07053","title":"Image Synthesis via Semantic Composition","created":"2021-09-15","cited_by_count":45},{"id":"1810.08476","title":"Improving Fast Segmentation With Teacher-student Learning","created":"2018-10-19","cited_by_count":34},{"id":"2301.01296","title":"TinyMIM: An Empirical Study of Distilling MIM Pre-trained Models","created":"2023-01-03","cited_by_count":24},{"id":"2004.11373","title":"Conditional Variational Image Deraining","created":"2020-04-23","cited_by_count":22},{"id":"1905.10117","title":"Robust Semantic Segmentation in Adverse Weather Conditions by means of Sensor Data Fusion","created":"2019-05-24","cited_by_count":18},{"id":"1807.02323","title":"Optimal Sensor Data Fusion Architecture for Object Detection in Adverse Weather Conditions","created":"2018-07-06","cited_by_count":11},{"id":"2010.10661","title":"Exploring Overcomplete Representations for Single Image Deraining using CNNs","created":"2020-10-20","cited_by_count":11},{"id":"1603.05691","title":"Do Deep Convolutional Nets Really Need to be Deep and Convolutional?","created":"2016-03-17","cited_by_count":8},{"id":"2109.07100","title":"Complementary Feature Enhanced Network with Vision Transformer for Image Dehazing","created":"2021-09-15","cited_by_count":8}],"next_cursor":null}