{"list":"other","total":71,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"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":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"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":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"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":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"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":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"id":"1712.09867","title":"Future Frame Prediction for Anomaly Detection -- A New Baseline","created":"2017-12-28","cited_by_count":391},{"id":"1904.11492","title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","created":"2019-04-25","cited_by_count":331},{"id":"1812.02707","title":"Video Action Transformer Network","created":"2018-12-06","cited_by_count":316},{"id":"1906.01787","title":"Learning Deep Transformer Models for Machine Translation","created":"2019-06-05","cited_by_count":309},{"id":"1904.02811","title":"Video Classification with Channel-Separated Convolutional Networks","created":"2019-04-04","cited_by_count":290},{"id":"2102.00719","title":"Video Transformer Network","created":"2021-02-01","cited_by_count":272},{"id":"1807.00230","title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization","created":"2018-06-30","cited_by_count":249},{"id":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"1909.04656","title":"Video Representation Learning by Dense Predictive Coding","created":"2019-09-10","cited_by_count":175},{"id":"1806.02919","title":"Non-Local Recurrent Network for Image Restoration","created":"2018-06-07","cited_by_count":160},{"id":"1811.09795","title":"Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles","created":"2018-11-24","cited_by_count":149},{"id":"1910.04744","title":"CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning","created":"2019-10-10","cited_by_count":137},{"id":"2008.01065","title":"Memory-augmented Dense Predictive Coding for Video Representation Learning","created":"2020-08-03","cited_by_count":137},{"id":"1905.00561","title":"Large-scale weakly-supervised pre-training for video action recognition","created":"2019-05-02","cited_by_count":130},{"id":"1912.04573","title":"Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagation","created":"2019-12-10","cited_by_count":125},{"id":"2005.02190","title":"Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video","created":"2020-05-04","cited_by_count":120},{"id":"2104.11746","title":"VidTr: Video Transformer Without Convolutions","created":"2021-04-23","cited_by_count":112},{"id":"2001.04583","title":"EGO-TOPO: Environment Affordances from Egocentric Video","created":"2020-01-14","cited_by_count":111},{"id":"1804.00892","title":"When will you do what? - Anticipating Temporal Occurrences of Activities","created":"2018-04-03","cited_by_count":107},{"id":"1905.09035","title":"What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention","created":"2019-05-22","cited_by_count":105},{"id":"1707.04818","title":"RED: Reinforced Encoder-Decoder Networks for Action Anticipation","created":"2017-07-16","cited_by_count":78},{"id":"1704.02895","title":"ActionVLAD: Learning spatio-temporal aggregation for action classification","created":"2017-04-10","cited_by_count":73},{"id":"1703.08132","title":"Weakly Supervised Action Learning with RNN based Fine-to-coarse Modeling","created":"2017-03-23","cited_by_count":70},{"id":"2101.10511","title":"Generic Event Boundary Detection: A Benchmark for Event Segmentation","created":"2021-01-26","cited_by_count":65},{"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":"1711.01467","title":"Attentional Pooling for Action Recognition","created":"2017-11-04","cited_by_count":54},{"id":"2102.00649","title":"Forecasting Action through Contact Representations from First Person Video","created":"2021-02-01","cited_by_count":46},{"id":"1505.02206","title":"Learning image representations tied to ego-motion","created":"2015-05-08","cited_by_count":42},{"id":"1509.05016","title":"Recurrent Neural Networks for Driver Activity Anticipation via Sensory-Fusion Architecture","created":"2015-09-16","cited_by_count":42},{"id":"1611.05109","title":"Low-rank Bilinear Pooling for Fine-Grained Classification","created":"2016-11-16","cited_by_count":42},{"id":"1912.07148","title":"Predicting the Future: A Jointly Learnt Model for Action Anticipation","created":"2019-12-16","cited_by_count":41},{"id":"1612.07796","title":"First-Person Activity Forecasting with Online Inverse Reinforcement Learning","created":"2016-12-22","cited_by_count":40},{"id":"2101.04924","title":"Learning to Anticipate Egocentric Actions by Imagination","created":"2021-01-13","cited_by_count":40},{"id":"1906.05743","title":"Learning Video Representations using Contrastive Bidirectional Transformer","created":"2019-06-13","cited_by_count":39},{"id":"1803.11496","title":"Predicting Future Instance Segmentation by Forecasting Convolutional Features","created":"2018-03-30","cited_by_count":37},{"id":"1711.09550","title":"Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification","created":"2017-11-27","cited_by_count":29},{"id":"1506.04714","title":"Slow and steady feature analysis: higher order temporal coherence in video","created":"2015-06-15","cited_by_count":28},{"id":"1911.07806","title":"Action Anticipation with RBF Kernelized Feature Mapping RNN","created":"2019-11-18","cited_by_count":20},{"id":"1808.00141","title":"Action Anticipation By Predicting Future Dynamic Images","created":"2018-08-01","cited_by_count":18},{"id":"2007.11040","title":"Directional Temporal Modeling for Action Recognition","created":"2020-07-21","cited_by_count":14},{"id":"2007.07306","title":"COBE: Contextualized Object Embeddings from Narrated Instructional Video","created":"2020-07-14","cited_by_count":12}],"next_cursor":null}