{"list":"other","total":58,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"id":"1604.05144","title":"ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation","created":"2016-04-18","cited_by_count":331},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"id":"1506.02106","title":"What's the Point: Semantic Segmentation with Point Supervision","created":"2015-06-06","cited_by_count":298},{"id":"1912.03590","title":"Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language","created":"2019-12-08","cited_by_count":285},{"id":"2004.13931","title":"Span-based Localizing Network for Natural Language Video Localization","created":"2020-04-29","cited_by_count":235},{"id":"2010.09709","title":"Self-supervised Co-training for Video Representation Learning","created":"2020-10-19","cited_by_count":232},{"id":"2004.07514","title":"Local-Global Video-Text Interactions for Temporal Grounding","created":"2020-04-16","cited_by_count":188},{"id":"1804.07014","title":"To Find Where You Talk: Temporal Sentence Localization in Video with Attention Based Location Regression","created":"2018-04-19","cited_by_count":157},{"id":"1812.00087","title":"MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment","created":"2018-11-30","cited_by_count":145},{"id":"1804.05113","title":"Multilevel Language and Vision Integration for Text-to-Clip Retrieval","created":"2018-04-13","cited_by_count":128},{"id":"2103.11555","title":"Context-aware Biaffine Localizing Network for Temporal Sentence Grounding","created":"2021-03-22","cited_by_count":107},{"id":"2106.11013","title":"Interventional Video Grounding with Dual Contrastive Learning","created":"2021-06-21","cited_by_count":94},{"id":"2103.08109","title":"Boundary Proposal Network for Two-Stage Natural Language Video Localization","created":"2021-03-15","cited_by_count":88},{"id":"1904.03282","title":"Weakly Supervised Video Moment Retrieval From Text Queries","created":"2019-04-05","cited_by_count":85},{"id":"1908.07236","title":"Proposal-free Temporal Moment Localization of a Natural-Language Query in Video using Guided Attention","created":"2019-08-20","cited_by_count":81},{"id":"1906.02497","title":"Cross-Modal Interaction Networks for Query-Based Moment Retrieval in Videos","created":"2019-06-06","cited_by_count":79},{"id":"2008.01403","title":"Jointly Cross- and Self-Modal Graph Attention Network for Query-Based Moment Localization","created":"2020-08-04","cited_by_count":74},{"id":"1911.08199","title":"Weakly-Supervised Video Moment Retrieval via Semantic Completion Network","created":"2019-11-19","cited_by_count":69},{"id":"1712.03162","title":"Class Rectification Hard Mining for Imbalanced Deep Learning","created":"2017-12-08","cited_by_count":67},{"id":"2003.06845","title":"SF-Net: Single-Frame Supervision for Temporal Action Localization","created":"2020-03-15","cited_by_count":62},{"id":"2203.13049","title":"Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning","created":"2022-03-24","cited_by_count":59},{"id":"2007.14164","title":"Learning Modality Interaction for Temporal Sentence Localization and Event Captioning in Videos","created":"2020-07-28","cited_by_count":56},{"id":"2102.13558","title":"Natural Language Video Localization: A Revisit in Span-based Question Answering Framework","created":"2021-02-26","cited_by_count":55},{"id":"1807.09856","title":"Where are the Blobs: Counting by Localization with Point Supervision","created":"2018-07-25","cited_by_count":54},{"id":"2109.06085","title":"On Pursuit of Designing Multi-modal Transformer for Video Grounding","created":"2021-09-13","cited_by_count":54},{"id":"1908.08216","title":"3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization","created":"2019-08-22","cited_by_count":52},{"id":"2107.05624","title":"End-to-end Multi-modal Video Temporal Grounding","created":"2021-07-12","cited_by_count":47},{"id":"2201.00454","title":"Memory-Guided Semantic Learning Network for Temporal Sentence Grounding","created":"2022-01-03","cited_by_count":46},{"id":"2108.05029","title":"Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization","created":"2021-08-11","cited_by_count":42},{"id":"2109.06398","title":"Adaptive Proposal Generation Network for Temporal Sentence Localization in Videos","created":"2021-09-14","cited_by_count":42},{"id":"2107.11443","title":"Cross-Sentence Temporal and Semantic Relations in Video Activity Localisation","created":"2021-07-23","cited_by_count":39},{"id":"2106.16136","title":"Weakly Supervised Temporal Adjacent Network for Language Grounding","created":"2021-06-30","cited_by_count":37},{"id":"2207.13457","title":"Reducing the Vision and Language Bias for Temporal Sentence Grounding","created":"2022-07-27","cited_by_count":35},{"id":"1811.02233","title":"Weakly Supervised Scene Parsing with Point-based Distance Metric Learning","created":"2018-11-06","cited_by_count":33},{"id":"2109.10016","title":"CONQUER: Contextual Query-aware Ranking for Video Corpus Moment Retrieval","created":"2021-09-21","cited_by_count":33},{"id":"1904.04689","title":"Action Recognition from Single Timestamp Supervision in Untrimmed Videos","created":"2019-04-09","cited_by_count":31},{"id":"2003.07048","title":"Weakly-Supervised Multi-Level Attentional Reconstruction Network for Grounding Textual Queries in Videos","created":"2020-03-16","cited_by_count":31},{"id":"2109.06400","title":"Progressively Guide to Attend: An Iterative Alignment Framework for Temporal Sentence Grounding","created":"2021-09-14","cited_by_count":31},{"id":"1505.05957","title":"Joint Inference of Groups, Events and Human Roles in Aerial Videos","created":"2015-05-22","cited_by_count":30},{"id":"2001.09308","title":"Look Closer to Ground Better: Weakly-Supervised Temporal Grounding of Sentence in Video","created":"2020-01-25","cited_by_count":29},{"id":"2201.00457","title":"Exploring Motion and Appearance Information for Temporal Sentence Grounding","created":"2022-01-03","cited_by_count":24},{"id":"1811.07460","title":"Segregated Temporal Assembly Recurrent Networks for Weakly Supervised Multiple Action Detection","created":"2018-11-19","cited_by_count":22},{"id":"2111.12449","title":"Background-Click Supervision for Temporal Action Localization","created":"2021-11-24","cited_by_count":21},{"id":"2012.08236","title":"Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses","created":"2020-12-15","cited_by_count":20},{"id":"2204.09409","title":"Video Moment Retrieval from Text Queries via Single Frame Annotation","created":"2022-04-20","cited_by_count":19},{"id":"2104.02357","title":"Adaptive Mutual Supervision for Weakly-Supervised Temporal Action Localization","created":"2021-04-06","cited_by_count":18},{"id":"1604.07602","title":"Spot On: Action Localization from Pointly-Supervised Proposals","created":"2016-04-26","cited_by_count":17},{"id":"1806.11328","title":"A flexible model for training action localization with varying levels of supervision","created":"2018-06-29","cited_by_count":16},{"id":"2212.09335","title":"Distilling Vision-Language Pre-training to Collaborate with Weakly-Supervised Temporal Action Localization","created":"2022-12-19","cited_by_count":12},{"id":"2008.09694","title":"Many-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object Detection","created":"2020-08-21","cited_by_count":4}],"next_cursor":null}