{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"1906.05849","title":"Contrastive Multiview Coding","created":"2019-06-13","cited_by_count":1301},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"1506.06724","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","created":"2015-06-22","cited_by_count":1043},{"id":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"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":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1911.05371","title":"Self-labelling via simultaneous clustering and representation learning","created":"2019-11-13","cited_by_count":528},{"id":"1611.05267","title":"Temporal Convolutional Networks for Action Segmentation and Detection","created":"2016-11-16","cited_by_count":508},{"id":"1912.06430","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","created":"2019-12-13","cited_by_count":507},{"id":"1909.11059","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","created":"2019-09-24","cited_by_count":494},{"id":"1908.06066","title":"Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training","created":"2019-08-16","cited_by_count":451},{"id":"1903.01945","title":"MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation","created":"2019-03-05","cited_by_count":373},{"id":"1912.02315","title":"12-in-1: Multi-Task Vision and Language Representation Learning","created":"2019-12-05","cited_by_count":278},{"id":"1703.01541","title":"Soft-DTW: a Differentiable Loss Function for Time-Series","created":"2017-03-05","cited_by_count":271},{"id":"1806.02964","title":"BSN: Boundary Sensitive Network for Temporal Action Proposal Generation","created":"2018-06-08","cited_by_count":271},{"id":"1704.06228","title":"Temporal Action Detection with Structured Segment Networks","created":"2017-04-20","cited_by_count":267},{"id":"2011.07231","title":"ActBERT: Learning Global-Local Video-Text Representations","created":"2020-11-14","cited_by_count":267},{"id":"2010.09709","title":"Self-supervised Co-training for Video Representation Learning","created":"2020-10-19","cited_by_count":232},{"id":"1909.11740","title":"UNITER: UNiversal Image-TExt Representation Learning","created":"2019-09-25","cited_by_count":228},{"id":"1903.08225","title":"Cross-task weakly supervised learning from instructional videos","created":"2019-03-19","cited_by_count":199},{"id":"1804.07667","title":"Rethinking the Faster R-CNN Architecture for Temporal Action Localization","created":"2018-04-20","cited_by_count":194},{"id":"1703.07814","title":"R-C3D: Region Convolutional 3D Network for Temporal Activity Detection","created":"2017-03-22","cited_by_count":161},{"id":"2108.09980","title":"TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment","created":"2021-08-23","cited_by_count":102},{"id":"1511.06984","title":"End-to-end Learning of Action Detection from Frame Glimpses in Videos","created":"2015-11-22","cited_by_count":101},{"id":"2103.16553","title":"Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers","created":"2021-03-30","cited_by_count":93},{"id":"1809.06181","title":"Dual Encoding for Zero-Example Video Retrieval","created":"2018-09-17","cited_by_count":85},{"id":"1901.02598","title":"D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation","created":"2019-01-09","cited_by_count":83},{"id":"1803.10699","title":"Weakly-Supervised Action Segmentation with Iterative Soft Boundary Assignment","created":"2018-03-28","cited_by_count":74},{"id":"2003.02824","title":"Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation","created":"2020-03-05","cited_by_count":74},{"id":"1607.08584","title":"Connectionist Temporal Modeling for Weakly Supervised Action Labeling","created":"2016-07-28","cited_by_count":70},{"id":"2104.09496","title":"Temporal Query Networks for Fine-grained Video Understanding","created":"2021-04-19","cited_by_count":68},{"id":"1805.06875","title":"NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video Learning","created":"2018-05-17","cited_by_count":67},{"id":"1505.01861","title":"Jointly Modeling Embedding and Translation to Bridge Video and Language","created":"2015-05-07","cited_by_count":53},{"id":"1909.13155","title":"Weakly Supervised Energy-Based Learning for Action Segmentation","created":"2019-09-28","cited_by_count":53},{"id":"1407.1208","title":"Weakly Supervised Action Labeling in Videos Under Ordering Constraints","created":"2014-07-04","cited_by_count":48},{"id":"2101.08540","title":"Activity Graph Transformer for Temporal Action Localization","created":"2021-01-21","cited_by_count":48},{"id":"1610.02237","title":"Weakly supervised learning of actions from transcripts","created":"2016-10-07","cited_by_count":46},{"id":"2103.10095","title":"On Semantic Similarity in Video Retrieval","created":"2021-03-18","cited_by_count":46},{"id":"1503.00949","title":"Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning","created":"2015-03-03","cited_by_count":39},{"id":"2108.11996","title":"Drop-DTW: Aligning Common Signal Between Sequences While Dropping Outliers","created":"2021-08-26","cited_by_count":39},{"id":"2103.09458","title":"Learning Discriminative Prototypes with Dynamic Time Warping","created":"2021-03-17","cited_by_count":23},{"id":"1505.06027","title":"Weakly-Supervised Alignment of Video With Text","created":"2015-05-22","cited_by_count":21}],"next_cursor":null}