{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"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":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"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":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1609.04802","title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","created":"2016-09-15","cited_by_count":1908},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"1511.00561","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","created":"2015-11-02","cited_by_count":1487},{"id":"1807.02758","title":"Image Super-Resolution Using Very Deep Residual Channel Attention Networks","created":"2018-07-08","cited_by_count":1264},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1711.09078","title":"Video Enhancement with Task-Oriented Flow","created":"2017-11-24","cited_by_count":619},{"id":"1611.06612","title":"RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation","created":"2016-11-20","cited_by_count":465},{"id":"1804.02815","title":"Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform","created":"2018-04-09","cited_by_count":371},{"id":"1902.06068","title":"Deep Learning for Image Super-resolution: A Survey","created":"2019-02-16","cited_by_count":369},{"id":"1510.04389","title":"Sketch-based Manga Retrieval using Manga109 Dataset","created":"2015-10-15","cited_by_count":329},{"id":"1907.06987","title":"A Short Note on the Kinetics-700 Human Action Dataset","created":"2019-07-15","cited_by_count":310},{"id":"1904.02811","title":"Video Classification with Channel-Separated Convolutional Networks","created":"2019-04-04","cited_by_count":290},{"id":"2003.05534","title":"Softmax Splatting for Video Frame Interpolation","created":"2020-03-11","cited_by_count":279},{"id":"2008.08767","title":"Single Image Super-Resolution via a Holistic Attention Network","created":"2020-08-20","cited_by_count":265},{"id":"1904.00830","title":"Depth-Aware Video Frame Interpolation","created":"2019-04-01","cited_by_count":234},{"id":"1702.08502","title":"Understanding Convolution for Semantic Segmentation","created":"2017-02-27","cited_by_count":168},{"id":"1803.10967","title":"Context-aware Synthesis for Video Frame Interpolation","created":"2018-03-29","cited_by_count":153},{"id":"2103.16206","title":"XVFI: eXtreme Video Frame Interpolation","created":"2021-03-30","cited_by_count":126},{"id":"1611.09326","title":"The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation","created":"2016-11-28","cited_by_count":122},{"id":"2007.12622","title":"BMBC:Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation","created":"2020-07-17","cited_by_count":118},{"id":"2007.11803","title":"MuCAN: Multi-Correspondence Aggregation Network for Video Super-Resolution","created":"2020-07-23","cited_by_count":89},{"id":"2106.02299","title":"MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution","created":"2021-06-04","cited_by_count":80},{"id":"2103.10559","title":"CDFI: Compression-Driven Network Design for Frame Interpolation","created":"2021-03-18","cited_by_count":56},{"id":"1912.00998","title":"A Multigrid Method for Efficiently Training Video Models","created":"2019-12-02","cited_by_count":52},{"id":"1301.3557","title":"Stochastic Pooling for Regularization of Deep Convolutional Neural Networks","created":"2013-01-16","cited_by_count":48},{"id":"1509.08985","title":"Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree","created":"2015-09-30","cited_by_count":36},{"id":"2105.12414","title":"Anticipating human actions by correlating past with the future with Jaccard similarity measures","created":"2021-05-26","cited_by_count":36},{"id":"1311.1780","title":"Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks","created":"2013-11-07","cited_by_count":32},{"id":"2004.04968","title":"Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?","created":"2020-04-10","cited_by_count":31},{"id":"1908.04156","title":"LIP: Local Importance-based Pooling","created":"2019-08-12","cited_by_count":30},{"id":"1804.04076","title":"Detail-Preserving Pooling in Deep Networks","created":"2018-04-11","cited_by_count":26},{"id":"2101.00440","title":"Refining activation downsampling with SoftPool","created":"2021-01-02","cited_by_count":26},{"id":"1611.05138","title":"S3Pool: Pooling with Stochastic Spatial Sampling","created":"2016-11-16","cited_by_count":17},{"id":"1311.4025","title":"Signal Recovery from Pooling Representations","created":"2013-11-16","cited_by_count":12},{"id":"2104.00996","title":"LiftPool: Bidirectional ConvNet Pooling","created":"2021-04-02","cited_by_count":11},{"id":"2006.08247","title":"Learn to cycle: Time-consistent feature discovery for action recognition","created":"2020-06-15","cited_by_count":8},{"id":"2011.03949","title":"Multi-Temporal Convolutions for Human Action Recognition in Videos","created":"2020-11-08","cited_by_count":1}],"next_cursor":null}