{"list":"other","total":91,"rows":[{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"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":"1710.10196","title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","created":"2017-10-27","cited_by_count":2988},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"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":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"2012.07436","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","created":"2020-12-14","cited_by_count":2169},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"1804.03999","title":"Attention U-Net: Learning Where to Look for the Pancreas","created":"2018-04-11","cited_by_count":1435},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"2201.12740","title":"FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting","created":"2022-01-30","cited_by_count":1210},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1609.04747","title":"An overview of gradient descent optimization algorithms","created":"2016-09-15","cited_by_count":1033},{"id":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"id":"1704.04110","title":"DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks","created":"2017-04-13","cited_by_count":1013},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"1703.07402","title":"Simple Online and Realtime Tracking with a Deep Association Metric","created":"2017-03-21","cited_by_count":910},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"2106.11959","title":"Revisiting Deep Learning Models for Tabular Data","created":"2021-06-22","cited_by_count":740},{"id":"1711.10485","title":"AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks","created":"2017-11-28","cited_by_count":664},{"id":"1908.07442","title":"TabNet: Attentive Interpretable Tabular Learning","created":"2019-08-20","cited_by_count":648},{"id":"1701.07875","title":"Wasserstein GAN","created":"2017-01-26","cited_by_count":639},{"id":"1606.09549","title":"Fully-Convolutional Siamese Networks for Object Tracking","created":"2016-06-30","cited_by_count":568},{"id":"2106.03253","title":"Tabular Data: Deep Learning is Not All You Need","created":"2021-06-06","cited_by_count":535},{"id":"2110.01889","title":"Deep Neural Networks and Tabular Data: A Survey","created":"2021-10-05","cited_by_count":491},{"id":"2004.01888","title":"FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking","created":"2020-04-04","cited_by_count":490},{"id":"2003.06505","title":"AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data","created":"2020-03-13","cited_by_count":383},{"id":"2012.15460","title":"TransTrack: Multiple Object Tracking with Transformer","created":"2020-12-31","cited_by_count":371},{"id":"1904.07220","title":"Learning Discriminative Model Prediction for Tracking","created":"2019-04-15","cited_by_count":344},{"id":"2106.09305","title":"SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction","created":"2021-06-17","cited_by_count":338},{"id":"2203.11991","title":"Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework","created":"2022-03-22","cited_by_count":330},{"id":"1911.07559","title":"FFA-Net: Feature Fusion Attention Network for Single Image Dehazing","created":"2019-11-18","cited_by_count":307},{"id":"1606.02147","title":"ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation","created":"2016-06-07","cited_by_count":291},{"id":"1811.07628","title":"ATOM: Accurate Tracking by Overlap Maximization","created":"2018-11-19","cited_by_count":285},{"id":"2106.14156","title":"Post-Training Quantization for Vision Transformer","created":"2021-06-27","cited_by_count":278},{"id":"2204.03883","title":"Vision Transformers for Single Image Dehazing","created":"2022-04-08","cited_by_count":260},{"id":"1610.09001","title":"SoundNet: Learning Sound Representations from Unlabeled Video","created":"2016-10-27","cited_by_count":247},{"id":"2203.15270","title":"MAT: Mask-Aware Transformer for Large Hole Image Inpainting","created":"2022-03-29","cited_by_count":218},{"id":"2006.14822","title":"A survey of loss functions for semantic segmentation","created":"2020-06-26","cited_by_count":217},{"id":"2101.11952","title":"Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss","created":"2021-01-28","cited_by_count":156},{"id":"2212.08254","title":"RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers","created":"2022-12-16","cited_by_count":137},{"id":"1909.06399","title":"Image inpainting: A review","created":"2019-09-13","cited_by_count":89},{"id":"1810.08771","title":"Image Inpainting via Generative Multi-column Convolutional Neural Networks","created":"2018-10-20","cited_by_count":81},{"id":"2305.03273","title":"Semantic Segmentation using Vision Transformers: A survey","created":"2023-05-05","cited_by_count":73},{"id":"2101.08158","title":"Focal and Efficient IOU Loss for Accurate Bounding Box Regression","created":"2021-01-20","cited_by_count":57},{"id":"2110.13389","title":"A Normalized Gaussian Wasserstein Distance for Tiny Object Detection","created":"2021-10-26","cited_by_count":53},{"id":"2308.09905","title":"DiffusionTrack: Diffusion Model For Multi-Object Tracking","created":"2023-08-19","cited_by_count":40},{"id":"2303.08524","title":"CoordFill: Efficient High-Resolution Image Inpainting via Parameterized Coordinate Querying","created":"2023-03-15","cited_by_count":34},{"id":"2312.05391","title":"Loss Functions in the Era of Semantic Segmentation: A Survey and Outlook","created":"2023-12-08","cited_by_count":34},{"id":"2211.02989","title":"A Comprehensive Survey of Regression Based Loss Functions for Time Series Forecasting","created":"2022-11-05","cited_by_count":33},{"id":"2111.06581","title":"Learning Quantile Functions without Quantile Crossing for Distribution-free Time Series Forecasting","created":"2021-11-12","cited_by_count":32},{"id":"2208.13049","title":"TrojViT: Trojan Insertion in Vision Transformers","created":"2022-08-27","cited_by_count":31},{"id":"2011.08018","title":"High-level Prior-based Loss Functions for Medical Image Segmentation: A Survey","created":"2020-11-16","cited_by_count":28},{"id":"2308.13767","title":"DiffI2I: Efficient Diffusion Model for Image-to-Image Translation","created":"2023-08-26","cited_by_count":24},{"id":"2306.02585","title":"MotionTrack: Learning Motion Predictor for Multiple Object Tracking","created":"2023-06-05","cited_by_count":20},{"id":"2107.03743","title":"Probabilistic Time Series Forecasting with Implicit Quantile Networks","created":"2021-07-08","cited_by_count":17},{"id":"2402.00033","title":"LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition","created":"2024-01-08","cited_by_count":13},{"id":"2105.03117","title":"Contrastive Learning for Unsupervised Image-to-Image Translation","created":"2021-05-07","cited_by_count":7},{"id":"2305.07239","title":"T-former: An Efficient Transformer for Image Inpainting","created":"2023-05-12","cited_by_count":7},{"id":"2407.00226","title":"Transformer-based Image and Video Inpainting: Current Challenges and Future Directions","created":"2024-06-28","cited_by_count":6},{"id":"2207.12121","title":"Cross-Modal Contrastive Representation Learning for Audio-to-Image Generation","created":"2022-07-20","cited_by_count":2},{"id":"2404.12948","title":"Next Generation Loss Function for Image Classification","created":"2024-04-19","cited_by_count":2},{"id":"2503.10287","title":"MACS: Multi-source Audio-to-image Generation with Contextual Significance and Semantic Alignment","created":"2025-03-13","cited_by_count":2}],"next_cursor":null}