{"list":"other","total":58,"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1906.05849","title":"Contrastive Multiview Coding","created":"2019-06-13","cited_by_count":1301},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"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":"2005.04966","title":"Prototypical Contrastive Learning of Unsupervised Representations","created":"2020-05-11","cited_by_count":640},{"id":"2010.04592","title":"Contrastive Learning with Hard Negative Samples","created":"2020-10-09","cited_by_count":628},{"id":"1704.06888","title":"Time-Contrastive Networks: Self-Supervised Learning from Video","created":"2017-04-23","cited_by_count":459},{"id":"1705.02953","title":"Temporal Segment Networks for Action Recognition in Videos","created":"2017-05-08","cited_by_count":279},{"id":"2104.13586","title":"Revisiting Skeleton-based Action Recognition","created":"2021-04-28","cited_by_count":257},{"id":"2010.09709","title":"Self-supervised Co-training for Video Representation Learning","created":"2020-10-19","cited_by_count":232},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232},{"id":"1708.01246","title":"Unsupervised Representation Learning by Sorting Sequences","created":"2017-08-03","cited_by_count":221},{"id":"2004.12943","title":"Audio-Visual Instance Discrimination with Cross-Modal Agreement","created":"2020-04-27","cited_by_count":195},{"id":"2004.06130","title":"SpeedNet: Learning the Speediness in Videos","created":"2020-04-13","cited_by_count":171},{"id":"1904.07846","title":"Temporal Cycle-Consistency Learning","created":"2019-04-16","cited_by_count":154},{"id":"1811.09795","title":"Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles","created":"2018-11-24","cited_by_count":149},{"id":"1506.09215","title":"Unsupervised Learning from Narrated Instruction Videos","created":"2015-06-30","cited_by_count":116},{"id":"2001.09691","title":"Multi-Modal Domain Adaptation for Fine-Grained Action Recognition","created":"2020-01-27","cited_by_count":115},{"id":"2103.16559","title":"Broaden Your Views for Self-Supervised Video Learning","created":"2021-03-30","cited_by_count":108},{"id":"1801.00054","title":"Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward","created":"2017-12-29","cited_by_count":105},{"id":"2006.11476","title":"Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation Learning","created":"2020-06-20","cited_by_count":103},{"id":"1902.11266","title":"Efficient Parameter-free Clustering Using First Neighbor Relations","created":"2019-02-28","cited_by_count":97},{"id":"2007.00394","title":"The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose","created":"2020-07-01","cited_by_count":95},{"id":"2007.10730","title":"Video Representation Learning by Recognizing Temporal Transformations","created":"2020-07-21","cited_by_count":83},{"id":"1911.11206","title":"Oops! Predicting Unintentional Action in Video","created":"2019-11-25","cited_by_count":82},{"id":"2207.10883","title":"My View is the Best View: Procedure Learning from Egocentric Videos","created":"2022-07-22","cited_by_count":81},{"id":"2010.05654","title":"The MECCANO Dataset: Understanding Human-Object Interactions from Egocentric Videos in an Industrial-like Domain","created":"2020-10-12","cited_by_count":79},{"id":"1904.04189","title":"Unsupervised learning of action classes with continuous temporal embedding","created":"2019-04-08","cited_by_count":76},{"id":"2109.14910","title":"CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations","created":"2021-09-30","cited_by_count":72},{"id":"1803.09490","title":"Unsupervised Learning and Segmentation of Complex Activities from Video","created":"2018-03-26","cited_by_count":61},{"id":"2103.17260","title":"Learning by Aligning Videos in Time","created":"2021-03-31","cited_by_count":48},{"id":"2001.11122","title":"Joint Visual-Temporal Embedding for Unsupervised Learning of Actions in Untrimmed Sequences","created":"2020-01-29","cited_by_count":45},{"id":"2011.10830","title":"Boundary-sensitive Pre-training for Temporal Localization in Videos","created":"2020-11-21","cited_by_count":41},{"id":"2108.02722","title":"Video Contrastive Learning with Global Context","created":"2021-08-05","cited_by_count":41},{"id":"1807.11293","title":"Improving Spatiotemporal Self-Supervision by Deep Reinforcement Learning","created":"2018-07-30","cited_by_count":35},{"id":"2003.04298","title":"On Compositions of Transformations in Contrastive Self-Supervised Learning","created":"2020-03-09","cited_by_count":34},{"id":"2008.11239","title":"HoloLens 2 Research Mode as a Tool for Computer Vision Research","created":"2020-08-25","cited_by_count":34},{"id":"2104.00682","title":"Multiview Pseudo-Labeling for Semi-supervised Learning from Video","created":"2021-04-01","cited_by_count":32},{"id":"1503.01558","title":"What's Cookin'? Interpreting Cooking Videos using Text, Speech and Vision","created":"2015-03-05","cited_by_count":31},{"id":"1912.06617","title":"Action Modifiers: Learning from Adverbs in Instructional Videos","created":"2019-12-13","cited_by_count":27},{"id":"2112.11450","title":"Max-Margin Contrastive Learning","created":"2021-12-21","cited_by_count":27},{"id":"2201.04029","title":"Motion-Focused Contrastive Learning of Video Representations","created":"2022-01-11","cited_by_count":23},{"id":"2005.03684","title":"Learning to Segment Actions from Observation and Narration","created":"2020-05-07","cited_by_count":21},{"id":"2111.09301","title":"Learning to Align Sequential Actions in the Wild","created":"2021-11-17","cited_by_count":20},{"id":"2112.03905","title":"ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpoints","created":"2021-12-07","cited_by_count":20},{"id":"2210.04135","title":"VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment","created":"2022-10-09","cited_by_count":20},{"id":"2010.08164","title":"Pose And Joint-Aware Action Recognition","created":"2020-10-16","cited_by_count":16},{"id":"1901.01153","title":"Demystifying Multi-Faceted Video Summarization: Tradeoff Between Diversity,Representation, Coverage and Importance","created":"2019-01-03","cited_by_count":14},{"id":"2008.02711","title":"Exploring Relations in Untrimmed Videos for Self-Supervised Learning","created":"2020-08-06","cited_by_count":11},{"id":"2104.14764","title":"CoCon: Cooperative-Contrastive Learning","created":"2021-04-30","cited_by_count":11},{"id":"1907.09382","title":"Domain-Specific Priors and Meta Learning for Few-Shot First-Person Action Recognition","created":"2019-07-22","cited_by_count":9},{"id":"1912.03650","title":"ILS-SUMM: Iterated Local Search for Unsupervised Video Summarization","created":"2019-12-08","cited_by_count":4},{"id":"2112.12182","title":"Fine-grained Multi-Modal Self-Supervised Learning","created":"2021-12-22","cited_by_count":4}],"next_cursor":null}