{"list":"other","total":52,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1802.01548","title":"Regularized Evolution for Image Classifier Architecture Search","created":"2018-02-05","cited_by_count":909},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"1712.00559","title":"Progressive Neural Architecture Search","created":"2017-12-02","cited_by_count":487},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"1705.09914","title":"Dilated Residual Networks","created":"2017-05-28","cited_by_count":294},{"id":"1806.01810","title":"Videos as Space-Time Region Graphs","created":"2018-06-05","cited_by_count":221},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"1708.07860","title":"Multi-task Self-Supervised Visual Learning","created":"2017-08-25","cited_by_count":200},{"id":"1804.09626","title":"Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos","created":"2018-04-25","cited_by_count":128},{"id":"2001.09691","title":"Multi-Modal Domain Adaptation for Fine-Grained Action Recognition","created":"2020-01-27","cited_by_count":115},{"id":"1712.00636","title":"Compressed Video Action Recognition","created":"2017-12-02","cited_by_count":106},{"id":"1904.01569","title":"Exploring Randomly Wired Neural Networks for Image Recognition","created":"2019-04-02","cited_by_count":103},{"id":"1709.06750","title":"SegFlow: Joint Learning for Video Object Segmentation and Optical Flow","created":"2017-09-20","cited_by_count":92},{"id":"1611.02155","title":"Spatiotemporal Residual Networks for Video Action Recognition","created":"2016-11-07","cited_by_count":91},{"id":"1810.02334","title":"Unsupervised Learning via Meta-Learning","created":"2018-10-04","cited_by_count":82},{"id":"2002.12177","title":"Evolving Losses for Unsupervised Video Representation Learning","created":"2020-02-26","cited_by_count":74},{"id":"1806.06157","title":"Object Level Visual Reasoning in Videos","created":"2018-06-16","cited_by_count":67},{"id":"1711.09125","title":"Appearance-and-Relation Networks for Video Classification","created":"2017-11-24","cited_by_count":61},{"id":"1711.09082","title":"Cross-Domain Self-supervised Multi-task Feature Learning using Synthetic Imagery","created":"2017-11-24","cited_by_count":56},{"id":"1810.01455","title":"Representation Flow for Action Recognition","created":"2018-10-02","cited_by_count":51},{"id":"1905.13209","title":"AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures","created":"2019-05-30","cited_by_count":46},{"id":"1412.0767","title":"Learning Spatiotemporal Features with 3D Convolutional Networks","created":"2014-12-02","cited_by_count":43},{"id":"1804.00413","title":"End-to-End Learning of Motion Representation for Video Understanding","created":"2018-04-02","cited_by_count":43},{"id":"1712.08416","title":"On the Integration of Optical Flow and Action Recognition","created":"2017-12-22","cited_by_count":42},{"id":"1704.00616","title":"Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection","created":"2017-04-03","cited_by_count":34},{"id":"1708.02696","title":"What Actions are Needed for Understanding Human Actions in Videos?","created":"2017-08-09","cited_by_count":29},{"id":"1910.06961","title":"Tiny Video Networks","created":"2019-10-15","cited_by_count":27},{"id":"1612.06371","title":"Asynchronous Temporal Fields for Action Recognition","created":"2016-12-19","cited_by_count":21},{"id":"1810.04511","title":"Interpretable Spatio-temporal Attention for Video Action Recognition","created":"2018-10-01","cited_by_count":20},{"id":"1707.09145","title":"Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions","created":"2017-07-28","cited_by_count":19},{"id":"1612.03052","title":"ActionFlowNet: Learning Motion Representation for Action Recognition","created":"2016-12-09","cited_by_count":18},{"id":"1811.10636","title":"Evolving Space-Time Neural Architectures for Videos","created":"2018-11-26","cited_by_count":17},{"id":"1904.11451","title":"Large Scale Holistic Video Understanding","created":"2019-04-25","cited_by_count":12},{"id":"1904.02371","title":"Architecture Search of Dynamic Cells for Semantic Video Segmentation","created":"2019-04-04","cited_by_count":5}],"next_cursor":null}