{"list":"other","total":53,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"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":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"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":"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":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232},{"id":"2005.08514","title":"Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction","created":"2020-05-18","cited_by_count":218},{"id":"2201.08377","title":"Omnivore: A Single Model for Many Visual Modalities","created":"2022-01-20","cited_by_count":215},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205},{"id":"2106.02036","title":"Anticipative Video Transformer","created":"2021-06-03","cited_by_count":200},{"id":"2303.16058","title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","created":"2023-03-28","cited_by_count":199},{"id":"2201.08383","title":"MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition","created":"2022-01-20","cited_by_count":189},{"id":"2106.10271","title":"End-to-end Temporal Action Detection with Transformer","created":"2021-06-18","cited_by_count":151},{"id":"2211.09552","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","created":"2022-11-17","cited_by_count":116},{"id":"2305.13292","title":"VideoLLM: Modeling Video Sequence with Large Language Models","created":"2023-05-22","cited_by_count":116},{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115},{"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":"2104.11746","title":"VidTr: Video Transformer Without Convolutions","created":"2021-04-23","cited_by_count":112},{"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":"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":"2203.16434","title":"TubeDETR: Spatio-Temporal Video Grounding with Transformers","created":"2022-03-30","cited_by_count":98},{"id":"2308.02236","title":"FB-BEV: BEV Representation from Forward-Backward View Transformations","created":"2023-08-04","cited_by_count":98},{"id":"2107.03377","title":"Long Short-Term Transformer for Online Action Detection","created":"2021-07-07","cited_by_count":88},{"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":"1803.09125","title":"Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition","created":"2018-03-24","cited_by_count":78},{"id":"2106.00515","title":"KVT: k-NN Attention for Boosting Vision Transformers","created":"2021-05-28","cited_by_count":65},{"id":"2209.09236","title":"Real-time Online Video Detection with Temporal Smoothing Transformers","created":"2022-09-19","cited_by_count":58},{"id":"1901.01874","title":"Mutual Context Network for Jointly Estimating Egocentric Gaze and Actions","created":"2019-01-07","cited_by_count":54},{"id":"2211.09529","title":"InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges","created":"2022-11-17","cited_by_count":48},{"id":"1912.04461","title":"Learning to Discriminate Information for Online Action Detection","created":"2019-12-10","cited_by_count":37},{"id":"2207.05515","title":"Compound Prototype Matching for Few-shot Action Recognition","created":"2022-07-12","cited_by_count":35},{"id":"2206.04668","title":"GateHUB: Gated History Unit with Background Suppression for Online Action Detection","created":"2022-06-09","cited_by_count":27},{"id":"2203.01057","title":"Colar: Effective and Efficient Online Action Detection by Consulting Exemplars","created":"2022-03-02","cited_by_count":21},{"id":"2006.03732","title":"WOAD: Weakly Supervised Online Action Detection in Untrimmed Videos","created":"2020-06-05","cited_by_count":19},{"id":"2011.09158","title":"Privileged Knowledge Distillation for Online Action Detection","created":"2020-11-18","cited_by_count":18},{"id":"2109.03393","title":"Learning to Discriminate Information for Online Action Detection: Analysis and Application","created":"2021-09-08","cited_by_count":6},{"id":"2208.14209","title":"A Circular Window-based Cascade Transformer for Online Action Detection","created":"2022-08-30","cited_by_count":4}],"next_cursor":null}