{"list":"other","total":73,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"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":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"1603.09246","title":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles","created":"2016-03-30","cited_by_count":1382},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"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":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"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":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1505.05192","title":"Unsupervised Visual Representation Learning by Context Prediction","created":"2015-05-19","cited_by_count":1066},{"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":"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":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"id":"2007.10639","title":"Multi-modal Transformer for Video Retrieval","created":"2020-07-21","cited_by_count":395},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"2010.09709","title":"Self-supervised Co-training for Video Representation Learning","created":"2020-10-19","cited_by_count":232},{"id":"2005.00343","title":"The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines","created":"2020-04-29","cited_by_count":225},{"id":"2106.05392","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","created":"2021-06-09","cited_by_count":224},{"id":"1806.01810","title":"Videos as Space-Time Region Graphs","created":"2018-06-05","cited_by_count":221},{"id":"2201.08377","title":"Omnivore: A Single Model for Many Visual Modalities","created":"2022-01-20","cited_by_count":215},{"id":"2012.10071","title":"TDN: Temporal Difference Networks for Efficient Action Recognition","created":"2020-12-18","cited_by_count":183},{"id":"2112.01529","title":"BEVT: BERT Pretraining of Video Transformers","created":"2021-12-02","cited_by_count":169},{"id":"2004.03548","title":"Temporal Pyramid Network for Action Recognition","created":"2020-04-07","cited_by_count":163},{"id":"2201.04288","title":"Multiview Transformers for Video Recognition","created":"2022-01-12","cited_by_count":148},{"id":"2104.07658","title":"Self-supervised Video Object Segmentation by Motion Grouping","created":"2021-04-15","cited_by_count":147},{"id":"2008.05861","title":"Self-supervised Video Representation Learning by Pace Prediction","created":"2020-08-13","cited_by_count":139},{"id":"1912.09930","title":"Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks","created":"2019-12-20","cited_by_count":114},{"id":"2206.10207","title":"SemMAE: Semantic-Guided Masking for Learning Masked Autoencoders","created":"2022-06-21","cited_by_count":114},{"id":"2206.11894","title":"MaskViT: Masked Visual Pre-Training for Video Prediction","created":"2022-06-23","cited_by_count":114},{"id":"2206.08356","title":"OmniMAE: Single Model Masked Pretraining on Images and Videos","created":"2022-06-16","cited_by_count":99},{"id":"1904.03597","title":"Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics","created":"2019-04-07","cited_by_count":92},{"id":"1604.04494","title":"Long-term Temporal Convolutions for Action Recognition","created":"2016-04-15","cited_by_count":84},{"id":"1909.07061","title":"Motion Guided Attention for Video Salient Object Detection","created":"2019-09-16","cited_by_count":72},{"id":"2007.09933","title":"MotionSqueeze: Neural Motion Feature Learning for Video Understanding","created":"2020-07-20","cited_by_count":72},{"id":"1906.05571","title":"Learning Spatio-Temporal Representation with Local and Global Diffusion","created":"2019-06-13","cited_by_count":61},{"id":"2108.02432","title":"Token Shift Transformer for Video Classification","created":"2021-08-05","cited_by_count":61},{"id":"2206.07990","title":"Patch-level Representation Learning for Self-supervised Vision Transformers","created":"2022-06-16","cited_by_count":60},{"id":"2106.11250","title":"VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning","created":"2021-06-21","cited_by_count":56},{"id":"1506.02897","title":"Flowing ConvNets for Human Pose Estimation in Videos","created":"2015-06-09","cited_by_count":55},{"id":"2208.00449","title":"SdAE: Self-distillated Masked Autoencoder","created":"2022-07-31","cited_by_count":52},{"id":"1605.03688","title":"Going Deeper into First-Person Activity Recognition","created":"2016-05-12","cited_by_count":48},{"id":"2205.07844","title":"Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motion","created":"2022-05-16","cited_by_count":42},{"id":"2001.05425","title":"UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking","created":"2020-01-15","cited_by_count":34},{"id":"2101.06553","title":"Self-Supervised Representation Learning from Flow Equivariance","created":"2021-01-16","cited_by_count":28},{"id":"2002.03137","title":"Symbiotic Attention with Privileged Information for Egocentric Action Recognition","created":"2020-02-08","cited_by_count":27},{"id":"2001.04627","title":"Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors","created":"2020-01-14","cited_by_count":24},{"id":"2207.10075","title":"Is an Object-Centric Video Representation Beneficial for Transfer?","created":"2022-07-20","cited_by_count":24},{"id":"2201.04029","title":"Motion-Focused Contrastive Learning of Video Representations","created":"2022-01-11","cited_by_count":23},{"id":"2206.09852","title":"M&M Mix: A Multimodal Multiview Transformer Ensemble","created":"2022-06-20","cited_by_count":20},{"id":"2205.13313","title":"Cross-Architecture Self-supervised Video Representation Learning","created":"2022-05-26","cited_by_count":13},{"id":"2212.03597","title":"DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing","created":"2022-12-07","cited_by_count":13},{"id":"2203.05997","title":"Towards Self-Supervised Learning of Global and Object-Centric Representations","created":"2022-03-11","cited_by_count":11},{"id":"2208.06105","title":"Motion Sensitive Contrastive Learning for Self-supervised Video Representation","created":"2022-08-12","cited_by_count":11},{"id":"2003.14065","title":"Long Short-Term Relation Networks for Video Action Detection","created":"2020-03-31","cited_by_count":10},{"id":"2007.10321","title":"Hierarchical Contrastive Motion Learning for Video Action Recognition","created":"2020-07-20","cited_by_count":8},{"id":"2204.04796","title":"SOS! Self-supervised Learning Over Sets Of Handled Objects In Egocentric Action Recognition","created":"2022-04-10","cited_by_count":8}],"next_cursor":null}