{"list":"other","total":88,"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":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"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":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"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":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1508.04025","title":"Effective Approaches to Attention-based Neural Machine Translation","created":"2015-08-17","cited_by_count":1026},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1805.08318","title":"Self-Attention Generative Adversarial Networks","created":"2018-05-21","cited_by_count":809},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1905.04757","title":"NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding","created":"2019-05-12","cited_by_count":533},{"id":"1511.08458","title":"An Introduction to Convolutional Neural Networks","created":"2015-11-26","cited_by_count":514},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"1812.02707","title":"Video Action Transformer Network","created":"2018-12-06","cited_by_count":316},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"id":"1907.06987","title":"A Short Note on the Kinetics-700 Human Action Dataset","created":"2019-07-15","cited_by_count":310},{"id":"2104.13586","title":"Revisiting Skeleton-based Action Recognition","created":"2021-04-28","cited_by_count":257},{"id":"1806.11230","title":"Human Action Recognition and Prediction: A Survey","created":"2018-06-28","cited_by_count":227},{"id":"1506.00019","title":"A Critical Review of Recurrent Neural Networks for Sequence Learning","created":"2015-05-29","cited_by_count":224},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"2201.08377","title":"Omnivore: A Single Model for Many Visual Modalities","created":"2022-01-20","cited_by_count":215},{"id":"2106.02036","title":"Anticipative Video Transformer","created":"2021-06-03","cited_by_count":200},{"id":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184},{"id":"2110.08568","title":"ASFormer: Transformer for Action Segmentation","created":"2021-10-16","cited_by_count":168},{"id":"2012.11866","title":"Human Action Recognition from Various Data Modalities: A Review","created":"2020-12-22","cited_by_count":163},{"id":"2106.10271","title":"End-to-end Temporal Action Detection with Transformer","created":"2021-06-18","cited_by_count":151},{"id":"2201.04288","title":"Multiview Transformers for Video Recognition","created":"2022-01-12","cited_by_count":148},{"id":"2106.11297","title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","created":"2021-06-21","cited_by_count":127},{"id":"2102.01894","title":"Relaxed Transformer Decoders for Direct Action Proposal Generation","created":"2021-02-03","cited_by_count":117},{"id":"2104.11746","title":"VidTr: Video Transformer Without Convolutions","created":"2021-04-23","cited_by_count":112},{"id":"1909.09586","title":"Understanding LSTM -- a tutorial into Long Short-Term Memory Recurrent Neural Networks","created":"2019-09-12","cited_by_count":103},{"id":"2003.12737","title":"Actor-Transformers for Group Activity Recognition","created":"2020-03-28","cited_by_count":84},{"id":"2106.11149","title":"OadTR: Online Action Detection with Transformers","created":"2021-06-21","cited_by_count":83},{"id":"2112.04446","title":"Everything at Once -- Multi-modal Fusion Transformer for Video Retrieval","created":"2021-12-08","cited_by_count":79},{"id":"2012.06399","title":"Spatial Temporal Transformer Network for Skeleton-based Action Recognition","created":"2020-12-11","cited_by_count":77},{"id":"1604.06506","title":"Online Action Detection","created":"2016-04-21","cited_by_count":69},{"id":"2205.14022","title":"Future Transformer for Long-term Action Anticipation","created":"2022-05-27","cited_by_count":58},{"id":"2104.00969","title":"TubeR: Tubelet Transformer for Video Action Detection","created":"2021-04-02","cited_by_count":55},{"id":"2002.07526","title":"A Survey of Deep Learning Techniques for Neural Machine Translation","created":"2020-02-18","cited_by_count":50},{"id":"2203.14104","title":"Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos","created":"2022-03-26","cited_by_count":50},{"id":"2101.08540","title":"Activity Graph Transformer for Temporal Action Localization","created":"2021-01-21","cited_by_count":48},{"id":"2108.09322","title":"MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition","created":"2021-08-20","cited_by_count":46},{"id":"2112.03902","title":"MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection","created":"2021-12-07","cited_by_count":42},{"id":"2111.01024","title":"With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition","created":"2021-11-01","cited_by_count":41},{"id":"2112.07175","title":"Co-training Transformer with Videos and Images Improves Action Recognition","created":"2021-12-14","cited_by_count":41},{"id":"2003.14266","title":"SCT: Set Constrained Temporal Transformer for Set Supervised Action Segmentation","created":"2020-03-31","cited_by_count":39},{"id":"2203.14240","title":"Audio-Adaptive Activity Recognition Across Video Domains","created":"2022-03-27","cited_by_count":35},{"id":"2203.10233","title":"DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition","created":"2022-03-19","cited_by_count":31},{"id":"2207.09270","title":"Action Quality Assessment with Temporal Parsing Transformer","created":"2022-07-19","cited_by_count":31},{"id":"2206.04668","title":"GateHUB: Gated History Unit with Background Suppression for Online Action Detection","created":"2022-06-09","cited_by_count":27},{"id":"2003.13594","title":"Speech2Action: Cross-modal Supervision for Action Recognition","created":"2020-03-30","cited_by_count":26},{"id":"2206.09852","title":"M&M Mix: A Multimodal Multiview Transformer Ensemble","created":"2022-06-20","cited_by_count":20},{"id":"2207.10448","title":"An Efficient Spatio-Temporal Pyramid Transformer for Action Detection","created":"2022-07-21","cited_by_count":16},{"id":"2203.16795","title":"Deformable Video Transformer","created":"2022-03-31","cited_by_count":15},{"id":"2205.01657","title":"Cross-modal Representation Learning for Zero-shot Action Recognition","created":"2022-05-03","cited_by_count":15},{"id":"2207.10388","title":"NSNet: Non-saliency Suppression Sampler for Efficient Video Recognition","created":"2022-07-21","cited_by_count":15},{"id":"2205.09445","title":"Cross-Enhancement Transformer for Action Segmentation","created":"2022-05-19","cited_by_count":14},{"id":"2204.04564","title":"Multimodal Transformer for Nursing Activity Recognition","created":"2022-04-09","cited_by_count":12},{"id":"1905.08711","title":"Lightweight Network Architecture for Real-Time Action Recognition","created":"2019-05-21","cited_by_count":10},{"id":"2205.05854","title":"Entity-aware and Motion-aware Transformers for Language-driven Action Localization in Videos","created":"2022-05-12","cited_by_count":10},{"id":"2207.12842","title":"Unsupervised Domain Adaptation for Video Transformers in Action Recognition","created":"2022-07-26","cited_by_count":10},{"id":"1308.6604","title":"A smart local moving algorithm for large-scale modularity-based community detection","created":"2013-08-29","cited_by_count":9},{"id":"2207.10379","title":"Temporal Saliency Query Network for Efficient Video Recognition","created":"2022-07-21","cited_by_count":9},{"id":"2107.07089","title":"STAR: Sparse Transformer-based Action Recognition","created":"2021-07-15","cited_by_count":8},{"id":"2206.01009","title":"Unified Recurrence Modeling for Video Action Anticipation","created":"2022-06-02","cited_by_count":7},{"id":"2104.08665","title":"Higher Order Recurrent Space-Time Transformer for Video Action Prediction","created":"2021-04-17","cited_by_count":6},{"id":"2111.09641","title":"Evaluating Transformers for Lightweight Action Recognition","created":"2021-11-18","cited_by_count":4},{"id":"2201.05675","title":"Transformers in Action: Weakly Supervised Action Segmentation","created":"2022-01-14","cited_by_count":4},{"id":"2201.06734","title":"Cross-modal Contrastive Distillation for Instructional Activity Anticipation","created":"2022-01-18","cited_by_count":4},{"id":"2208.01753","title":"Two-Stream Transformer Architecture for Long Video Understanding","created":"2022-08-02","cited_by_count":4},{"id":"2208.01897","title":"Combined CNN Transformer Encoder for Enhanced Fine-grained Human Action Recognition","created":"2022-08-03","cited_by_count":4},{"id":"2106.13014","title":"Exploring Stronger Feature for Temporal Action Localization","created":"2021-06-24","cited_by_count":3},{"id":"2107.00451","title":"VideoLightFormer: Lightweight Action Recognition using Transformers","created":"2021-07-01","cited_by_count":3}],"next_cursor":null}