{"list":"other","total":56,"rows":[{"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1602.07261","title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning","created":"2016-02-23","cited_by_count":1512},{"id":"1511.00561","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","created":"2015-11-02","cited_by_count":1487},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"1803.01534","title":"Path Aggregation Network for Instance Segmentation","created":"2018-03-05","cited_by_count":798},{"id":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"1711.02512","title":"Fine-tuning CNN Image Retrieval with No Human Annotation","created":"2017-11-03","cited_by_count":499},{"id":"1707.06484","title":"Deep Layer Aggregation","created":"2017-07-20","cited_by_count":436},{"id":"1703.02719","title":"Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network","created":"2017-03-08","cited_by_count":208},{"id":"1702.08502","title":"Understanding Convolution for Semantic Segmentation","created":"2017-02-27","cited_by_count":168},{"id":"2101.04775","title":"Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis","created":"2021-01-12","cited_by_count":140},{"id":"1810.06553","title":"Recipe1M+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images","created":"2018-10-14","cited_by_count":118},{"id":"1809.00287","title":"Learning to Navigate for Fine-grained Classification","created":"2018-09-02","cited_by_count":103},{"id":"2004.06002","title":"Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training","created":"2020-04-13","cited_by_count":103},{"id":"2003.03836","title":"Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches","created":"2020-03-08","cited_by_count":92},{"id":"1808.07202","title":"A Survey on Food Computing","created":"2018-08-22","cited_by_count":59},{"id":"2103.03375","title":"Nutrition5k: Towards Automatic Nutritional Understanding of Generic Food","created":"2021-03-04","cited_by_count":58},{"id":"1901.09891","title":"See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification","created":"2019-01-26","cited_by_count":56},{"id":"1807.09915","title":"Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition","created":"2018-07-26","cited_by_count":47},{"id":"1812.06164","title":"Inverse Cooking: Recipe Generation from Food Images","created":"2018-12-14","cited_by_count":47},{"id":"2008.05655","title":"ISIA Food-500: A Dataset for Large-Scale Food Recognition via Stacked Global-Local Attention Network","created":"2020-08-13","cited_by_count":47},{"id":"1905.01273","title":"Learning Cross-Modal Embeddings with Adversarial Networks for Cooking Recipes and Food Images","created":"2019-05-03","cited_by_count":39},{"id":"1804.11146","title":"Cross-Modal Retrieval in the Cooking Context: Learning Semantic Text-Image Embeddings","created":"2018-04-30","cited_by_count":35},{"id":"1907.06167","title":"FoodX-251: A Dataset for Fine-grained Food Classification","created":"2019-07-14","cited_by_count":33},{"id":"2103.13061","title":"Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning","created":"2021-03-24","cited_by_count":28},{"id":"1705.02743","title":"ChineseFoodNet: A large-scale Image Dataset for Chinese Food Recognition","created":"2017-05-08","cited_by_count":21},{"id":"1906.02839","title":"How to make a pizza: Learning a compositional layer-based GAN model","created":"2019-06-06","cited_by_count":21},{"id":"1606.05675","title":"DeepFood: Deep Learning-Based Food Image Recognition for Computer-Aided Dietary Assessment","created":"2016-06-17","cited_by_count":19},{"id":"2009.00944","title":"Structure-Aware Generation Network for Recipe Generation from Images","created":"2020-09-02","cited_by_count":19},{"id":"1612.06543","title":"Wide-Slice Residual Networks for Food Recognition","created":"2016-12-20","cited_by_count":18},{"id":"1909.11946","title":"FoodAI: Food Image Recognition via Deep Learning for Smart Food Logging","created":"2019-09-26","cited_by_count":18},{"id":"2004.01095","title":"MCEN: Bridging Cross-Modal Gap between Cooking Recipes and Dish Images with Latent Variable Model","created":"2020-04-02","cited_by_count":16},{"id":"2003.13272","title":"Multi-Objective Matrix Normalization for Fine-grained Visual Recognition","created":"2020-03-30","cited_by_count":15},{"id":"1604.07953","title":"Simultaneous Food Localization and Recognition","created":"2016-04-27","cited_by_count":14},{"id":"2002.11493","title":"CookGAN: Meal Image Synthesis from Ingredients","created":"2020-02-25","cited_by_count":14},{"id":"1907.13075","title":"Pay attention to the activations: a modular attention mechanism for fine-grained image recognition","created":"2019-07-30","cited_by_count":12},{"id":"1711.05128","title":"Grab, Pay and Eat: Semantic Food Detection for Smart Restaurants","created":"2017-11-14","cited_by_count":11},{"id":"1709.09429","title":"FoodNet: Recognizing Foods Using Ensemble of Deep Networks","created":"2017-09-27","cited_by_count":10},{"id":"1804.04600","title":"Personalized Classifier for Food Image Recognition","created":"2018-04-08","cited_by_count":9},{"id":"1512.02665","title":"Fine-grained Image Classification by Exploring Bipartite-Graph Labels","created":"2015-12-08","cited_by_count":8},{"id":"2003.08273","title":"An Artificial Intelligence-Based System to Assess Nutrient Intake for Hospitalised Patients","created":"2020-03-18","cited_by_count":7},{"id":"1912.05007","title":"Oktoberfest Food Dataset","created":"2019-11-22","cited_by_count":5},{"id":"1709.04864","title":"Food Recognition using Fusion of Classifiers based on CNNs","created":"2017-09-14","cited_by_count":3}],"next_cursor":null}