{"list":"other","total":52,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"2012.07436","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","created":"2020-12-14","cited_by_count":2169},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"2006.03677","title":"Visual Transformers: Token-based Image Representation and Processing for Computer Vision","created":"2020-06-05","cited_by_count":334},{"id":"1907.09702","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","created":"2019-07-23","cited_by_count":329},{"id":"2003.13228","title":"Learning Memory-guided Normality for Anomaly Detection","created":"2020-03-30","cited_by_count":278},{"id":"1806.02964","title":"BSN: Boundary Sensitive Network for Temporal Action Proposal Generation","created":"2018-06-08","cited_by_count":271},{"id":"1911.11462","title":"G-TAD: Sub-Graph Localization for Temporal Action Detection","created":"2019-11-26","cited_by_count":249},{"id":"1506.00019","title":"A Critical Review of Recurrent Neural Networks for Sequence Learning","created":"2015-05-29","cited_by_count":224},{"id":"1909.06317","title":"A Comparative Study on Transformer vs RNN in Speech Applications","created":"2019-09-13","cited_by_count":211},{"id":"1804.07667","title":"Rethinking the Faster R-CNN Architecture for Temporal Action Localization","created":"2018-04-20","cited_by_count":194},{"id":"1703.07814","title":"R-C3D: Region Convolutional 3D Network for Temporal Activity Detection","created":"2017-03-22","cited_by_count":161},{"id":"1710.06236","title":"Single Shot Temporal Action Detection","created":"2017-10-17","cited_by_count":123},{"id":"1703.01515","title":"CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos","created":"2017-03-04","cited_by_count":112},{"id":"2103.13141","title":"Temporal Context Aggregation Network for Temporal Action Proposal Refinement","created":"2021-03-24","cited_by_count":112},{"id":"2011.04233","title":"End-to-end Lane Shape Prediction with Transformers","created":"2020-11-09","cited_by_count":111},{"id":"2011.09315","title":"End-to-End Object Detection with Adaptive Clustering Transformer","created":"2020-11-18","cited_by_count":109},{"id":"1811.02307","title":"Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal Reasoning","created":"2018-11-06","cited_by_count":102},{"id":"1507.05738","title":"Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos","created":"2015-07-21","cited_by_count":93},{"id":"1911.04127","title":"Fast Learning of Temporal Action Proposal via Dense Boundary Generator","created":"2019-11-11","cited_by_count":89},{"id":"2008.01432","title":"Boundary Content Graph Neural Network for Temporal Action Proposal Generation","created":"2020-08-04","cited_by_count":88},{"id":"2003.06780","title":"Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detection","created":"2020-03-15","cited_by_count":83},{"id":"1811.07391","title":"Temporal Recurrent Networks for Online Action Detection","created":"2018-11-18","cited_by_count":80},{"id":"1707.04818","title":"RED: Reinforced Encoder-Decoder Networks for Action Anticipation","created":"2017-07-16","cited_by_count":78},{"id":"1911.06978","title":"Grounding Human-to-Vehicle Advice for Self-driving Vehicles","created":"2019-11-16","cited_by_count":71},{"id":"1604.06506","title":"Online Action Detection","created":"2016-04-21","cited_by_count":69},{"id":"2104.03214","title":"Self-Supervised Learning for Semi-Supervised Temporal Action Proposal","created":"2021-04-07","cited_by_count":39},{"id":"1912.04461","title":"Learning to Discriminate Information for Online Action Detection","created":"2019-12-10","cited_by_count":37},{"id":"2011.10185","title":"ConvTransformer: A Convolutional Transformer Network for Video Frame Synthesis","created":"2020-11-20","cited_by_count":34},{"id":"1505.05957","title":"Joint Inference of Groups, Events and Human Roles in Aerial Videos","created":"2015-05-22","cited_by_count":30},{"id":"1604.05633","title":"Online Human Action Detection using Joint Classification-Regression Recurrent Neural Networks","created":"2016-04-19","cited_by_count":28},{"id":"1903.09868","title":"StartNet: Online Detection of Action Start in Untrimmed Videos","created":"2019-03-23","cited_by_count":21},{"id":"1908.09442","title":"Deep Concept-wise Temporal Convolutional Networks for Action Localization","created":"2019-08-26","cited_by_count":10},{"id":"2008.03270","title":"Multi-Level Temporal Pyramid Network for Action Detection","created":"2020-08-07","cited_by_count":6}],"next_cursor":null}