{"list":"other","total":150,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1711.06396","title":"VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection","created":"2017-11-17","cited_by_count":1323},{"id":"1702.05747","title":"A Survey on Deep Learning in Medical Image Analysis","created":"2017-02-19","cited_by_count":1186},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"2302.00487","title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","created":"2023-01-31","cited_by_count":872},{"id":"1707.08114","title":"A Survey on Multi-Task Learning","created":"2017-07-25","cited_by_count":840},{"id":"1404.7828","title":"Deep Learning in Neural Networks: An Overview","created":"2014-04-30","cited_by_count":770},{"id":"1406.4729","title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","created":"2014-06-18","cited_by_count":720},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613},{"id":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"1807.05511","title":"Object Detection with Deep Learning: A Review","created":"2018-07-15","cited_by_count":528},{"id":"2209.12152","title":"All are Worth Words: A ViT Backbone for Diffusion Models","created":"2022-09-25","cited_by_count":502},{"id":"1711.08565","title":"Person Transfer GAN to Bridge Domain Gap for Person Re-Identification","created":"2017-11-23","cited_by_count":480},{"id":"1904.01169","title":"Res2Net: A New Multi-scale Backbone Architecture","created":"2019-04-02","cited_by_count":470},{"id":"1604.03539","title":"Cross-stitch Networks for Multi-task Learning","created":"2016-04-12","cited_by_count":467},{"id":"1708.08987","title":"Deep Learning for Medical Image Analysis","created":"2017-08-17","cited_by_count":401},{"id":"2004.02806","title":"A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects","created":"2020-04-01","cited_by_count":397},{"id":"2002.10179","title":"HRank: Filter Pruning using High-Rank Feature Map","created":"2020-02-24","cited_by_count":292},{"id":"1804.00175","title":"DeepIM: Deep Iterative Matching for 6D Pose Estimation","created":"2018-03-31","cited_by_count":283},{"id":"2006.16228","title":"Self-Supervised MultiModal Versatile Networks","created":"2020-06-29","cited_by_count":276},{"id":"2008.01449","title":"Prior Guided Feature Enrichment Network for Few-Shot Segmentation","created":"2020-08-04","cited_by_count":271},{"id":"2006.04647","title":"Neural Architecture Search without Training","created":"2020-06-08","cited_by_count":244},{"id":"1711.10006","title":"SSD-6D: Making RGB-based 3D detection and 6D pose estimation great again","created":"2017-11-27","cited_by_count":243},{"id":"2111.15668","title":"AdaViT: Adaptive Vision Transformers for Efficient Image Recognition","created":"2021-11-30","cited_by_count":228},{"id":"1903.02740","title":"CE-Net: Context Encoder Network for 2D Medical Image Segmentation","created":"2019-03-07","cited_by_count":220},{"id":"1901.06032","title":"A Survey of the Recent Architectures of Deep Convolutional Neural Networks","created":"2019-01-17","cited_by_count":213},{"id":"1611.10012","title":"Speed/accuracy trade-offs for modern convolutional object detectors","created":"2016-11-30","cited_by_count":198},{"id":"2011.01118","title":"U-Net and its variants for medical image segmentation: theory and applications","created":"2020-11-02","cited_by_count":169},{"id":"2205.06743","title":"A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities","created":"2022-05-13","cited_by_count":163},{"id":"2205.12952","title":"Pretraining is All You Need for Image-to-Image Translation","created":"2022-05-25","cited_by_count":160},{"id":"2304.00501","title":"A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS","created":"2023-04-02","cited_by_count":151},{"id":"2004.00605","title":"EPOS: Estimating 6D Pose of Objects with Symmetries","created":"2020-04-01","cited_by_count":148},{"id":"2203.12745","title":"UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection","created":"2022-03-23","cited_by_count":148},{"id":"2008.10937","title":"A Survey on Evolutionary Neural Architecture Search","created":"2020-08-25","cited_by_count":142},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139},{"id":"2106.02852","title":"Patch Slimming for Efficient Vision Transformers","created":"2021-06-05","cited_by_count":133},{"id":"2001.06202","title":"FedVision: An Online Visual Object Detection Platform Powered by Federated Learning","created":"2020-01-17","cited_by_count":124},{"id":"2103.14862","title":"TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization","created":"2021-03-27","cited_by_count":123},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122},{"id":"2212.08059","title":"Rethinking Vision Transformers for MobileNet Size and Speed","created":"2022-12-15","cited_by_count":121},{"id":"1812.10775","title":"3D Point Capsule Networks","created":"2018-12-27","cited_by_count":106},{"id":"1907.09408","title":"A Survey of Deep Learning-based Object Detection","created":"2019-07-11","cited_by_count":106},{"id":"2303.16509","title":"HoloDiffusion: Training a 3D Diffusion Model using 2D Images","created":"2023-03-29","cited_by_count":106},{"id":"1603.01249","title":"HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition","created":"2016-03-03","cited_by_count":104},{"id":"1709.02250","title":"Medical Image Analysis using Convolutional Neural Networks: A Review","created":"2017-09-04","cited_by_count":99},{"id":"2207.01405","title":"I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference","created":"2022-07-04","cited_by_count":95},{"id":"2108.06227","title":"SimCVD: Simple Contrastive Voxel-Wise Representation Distillation for Semi-Supervised Medical Image Segmentation","created":"2021-08-13","cited_by_count":86},{"id":"2111.09833","title":"TransMix: Attend to Mix for Vision Transformers","created":"2021-11-18","cited_by_count":79},{"id":"2108.09020","title":"Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data","created":"2021-08-20","cited_by_count":69},{"id":"1812.05840","title":"Spatial Fusion GAN for Image Synthesis","created":"2018-12-14","cited_by_count":68},{"id":"2211.14068","title":"Fine-Grained Face Swapping via Regional GAN Inversion","created":"2022-11-25","cited_by_count":67},{"id":"1906.09610","title":"Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments","created":"2019-06-23","cited_by_count":64},{"id":"2112.10809","title":"Lite Vision Transformer with Enhanced Self-Attention","created":"2021-12-20","cited_by_count":64},{"id":"2007.09990","title":"Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering","created":"2020-07-20","cited_by_count":61},{"id":"1907.03128","title":"Multi-level Wavelet Convolutional Neural Networks","created":"2019-07-06","cited_by_count":59},{"id":"2001.00139","title":"Handwritten Optical Character Recognition (OCR): A Comprehensive Systematic Literature Review (SLR)","created":"2020-01-01","cited_by_count":56},{"id":"2105.12374","title":"Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks","created":"2021-05-26","cited_by_count":56},{"id":"2011.13628","title":"Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving","created":"2020-11-27","cited_by_count":55},{"id":"1501.04560","title":"Transductive Multi-view Zero-Shot Learning","created":"2015-01-19","cited_by_count":53},{"id":"2203.11894","title":"GradViT: Gradient Inversion of Vision Transformers","created":"2022-03-22","cited_by_count":53},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52},{"id":"2003.14058","title":"MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning","created":"2020-03-31","cited_by_count":50},{"id":"2011.00241","title":"Methods for Pruning Deep Neural Networks","created":"2020-10-31","cited_by_count":49},{"id":"2101.02833","title":"Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition","created":"2021-01-08","cited_by_count":48},{"id":"2205.13137","title":"MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers","created":"2022-05-26","cited_by_count":47},{"id":"2103.04523","title":"Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization","created":"2021-03-08","cited_by_count":46},{"id":"1706.00906","title":"Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach","created":"2017-06-03","cited_by_count":43},{"id":"1904.09546","title":"DeepCaps: Going Deeper with Capsule Networks","created":"2019-04-21","cited_by_count":42},{"id":"2009.05868","title":"From Federated Learning to Federated Neural Architecture Search: A Survey","created":"2020-09-12","cited_by_count":42},{"id":"2209.05687","title":"PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformers","created":"2022-09-13","cited_by_count":42},{"id":"1908.07656","title":"Survey on Deep Neural Networks in Speech and Vision Systems","created":"2019-08-16","cited_by_count":37},{"id":"2012.11233","title":"Hardware and Software Optimizations for Accelerating Deep Neural Networks: Survey of Current Trends, Challenges, and the Road Ahead","created":"2020-12-21","cited_by_count":34},{"id":"2305.09880","title":"A survey of the Vision Transformers and their CNN-Transformer based Variants","created":"2023-05-17","cited_by_count":33},{"id":"2006.16471","title":"Object Detection Under Rainy Conditions for Autonomous Vehicles: A Review of State-of-the-Art and Emerging Techniques","created":"2020-06-30","cited_by_count":31},{"id":"2007.09479","title":"Deep Learning Based Brain Tumor Segmentation: A Survey","created":"2020-07-18","cited_by_count":30},{"id":"2110.05741","title":"Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localization","created":"2021-10-12","cited_by_count":30},{"id":"1805.08620","title":"Wavelet Convolutional Neural Networks","created":"2018-05-20","cited_by_count":29},{"id":"2203.11684","title":"Meta-attention for ViT-backed Continual Learning","created":"2022-03-22","cited_by_count":29},{"id":"1910.02543","title":"Improving One-shot NAS by Suppressing the Posterior Fading","created":"2019-10-06","cited_by_count":28},{"id":"2003.03143","title":"Triple Memory Networks: a Brain-Inspired Method for Continual Learning","created":"2020-03-06","cited_by_count":28},{"id":"2003.13549","title":"Rethinking Depthwise Separable Convolutions: How Intra-Kernel Correlations Lead to Improved MobileNets","created":"2020-03-30","cited_by_count":28},{"id":"2211.07091","title":"BiViT: Extremely Compressed Binary Vision Transformer","created":"2022-11-14","cited_by_count":28}],"next_cursor":"100"}