{"list":"other","total":66,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"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":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1906.05849","title":"Contrastive Multiview Coding","created":"2019-06-13","cited_by_count":1301},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"1912.06430","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","created":"2019-12-13","cited_by_count":507},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"2007.10639","title":"Multi-modal Transformer for Video Retrieval","created":"2020-07-21","cited_by_count":395},{"id":"1704.04497","title":"TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering","created":"2017-04-14","cited_by_count":378},{"id":"2006.06666","title":"VirTex: Learning Visual Representations from Textual Annotations","created":"2020-06-11","cited_by_count":339},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"1812.02707","title":"Video Action Transformer Network","created":"2018-12-06","cited_by_count":316},{"id":"2011.07231","title":"ActBERT: Learning Global-Local Video-Text Representations","created":"2020-11-14","cited_by_count":267},{"id":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"2004.06704","title":"FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding","created":"2020-04-14","cited_by_count":234},{"id":"1503.08909","title":"Beyond Short Snippets: Deep Networks for Video Classification","created":"2015-03-31","cited_by_count":233},{"id":"1806.01810","title":"Videos as Space-Time Region Graphs","created":"2018-06-05","cited_by_count":221},{"id":"1907.13487","title":"Use What You Have: Video Retrieval Using Representations From Collaborative Experts","created":"2019-07-31","cited_by_count":214},{"id":"1604.01850","title":"Joint Detection and Identification Feature Learning for Person Search","created":"2016-04-07","cited_by_count":190},{"id":"2003.00392","title":"Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning","created":"2020-03-01","cited_by_count":180},{"id":"2004.03548","title":"Temporal Pyramid Network for Action Recognition","created":"2020-04-07","cited_by_count":163},{"id":"1904.04289","title":"SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition","created":"2019-04-08","cited_by_count":134},{"id":"1912.05534","title":"Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition","created":"2019-12-11","cited_by_count":117},{"id":"1908.03477","title":"Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings","created":"2019-08-09","cited_by_count":101},{"id":"1604.04494","title":"Long-term Temporal Convolutions for Action Recognition","created":"2016-04-15","cited_by_count":84},{"id":"1906.03349","title":"Video Modeling with Correlation Networks","created":"2019-06-07","cited_by_count":73},{"id":"1607.08584","title":"Connectionist Temporal Modeling for Weakly Supervised Action Labeling","created":"2016-07-28","cited_by_count":70},{"id":"1607.01794","title":"VideoLSTM Convolves, Attends and Flows for Action Recognition","created":"2016-07-06","cited_by_count":60},{"id":"1706.06905","title":"Learnable pooling with Context Gating for video classification","created":"2017-06-21","cited_by_count":58},{"id":"2006.15489","title":"Video Representation Learning with Visual Tempo Consistency","created":"2020-06-28","cited_by_count":57},{"id":"1909.13130","title":"Grouped Spatial-Temporal Aggregation for Efficient Action Recognition","created":"2019-09-28","cited_by_count":55},{"id":"1912.03538","title":"Context R-CNN: Long Term Temporal Context for Per-Camera Object Detection","created":"2019-12-07","cited_by_count":45},{"id":"1707.06355","title":"Video Question Answering via Attribute-Augmented Attention Network Learning","created":"2017-07-20","cited_by_count":39},{"id":"2007.09861","title":"Context-Aware RCNN: A Baseline for Action Detection in Videos","created":"2020-07-20","cited_by_count":33},{"id":"1505.06027","title":"Weakly-Supervised Alignment of Video With Text","created":"2015-05-22","cited_by_count":21},{"id":"1612.06371","title":"Asynchronous Temporal Fields for Action Recognition","created":"2016-12-19","cited_by_count":21},{"id":"1904.08607","title":"Progressive Attention Memory Network for Movie Story Question Answering","created":"2019-04-18","cited_by_count":21},{"id":"1809.07999","title":"Multimodal Dual Attention Memory for Video Story Question Answering","created":"2018-09-21","cited_by_count":20},{"id":"1806.01873","title":"Focal Visual-Text Attention for Visual Question Answering","created":"2018-06-05","cited_by_count":19},{"id":"2007.08751","title":"Knowledge-Based Video Question Answering with Unsupervised Scene Descriptions","created":"2020-07-17","cited_by_count":15},{"id":"2007.10703","title":"Uncertainty-Aware Weakly Supervised Action Detection from Untrimmed Videos","created":"2020-07-21","cited_by_count":15},{"id":"1905.00050","title":"Attentive Spatio-Temporal Representation Learning for Diving Classification","created":"2019-04-30","cited_by_count":11},{"id":"2008.02129","title":"Self-supervised Temporal Discriminative Learning for Video Representation Learning","created":"2020-08-05","cited_by_count":9},{"id":"1810.00207","title":"Non-local NetVLAD Encoding for Video Classification","created":"2018-09-29","cited_by_count":8},{"id":"1707.04555","title":"Temporal Modeling Approaches for Large-scale Youtube-8M Video Understanding","created":"2017-07-14","cited_by_count":7},{"id":"1812.04172","title":"Learning Discriminative Motion Features Through Detection","created":"2018-12-11","cited_by_count":3},{"id":"1809.08381","title":"Learning to Localize and Align Fine-Grained Actions to Sparse Instructions","created":"2018-09-22","cited_by_count":1}],"next_cursor":null}