{"list":"other","total":81,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"1603.08511","title":"Colorful Image Colorization","created":"2016-03-28","cited_by_count":1114},{"id":"1505.05192","title":"Unsupervised Visual Representation Learning by Context Prediction","created":"2015-05-19","cited_by_count":1066},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"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":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"2008.03800","title":"Spatiotemporal Contrastive Video Representation Learning","created":"2020-08-09","cited_by_count":372},{"id":"1907.09702","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","created":"2019-07-23","cited_by_count":329},{"id":"1912.03590","title":"Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language","created":"2019-12-08","cited_by_count":285},{"id":"1606.00061","title":"Hierarchical Question-Image Co-Attention for Visual Question Answering","created":"2016-05-31","cited_by_count":278},{"id":"1704.06228","title":"Temporal Action Detection with Structured Segment Networks","created":"2017-04-20","cited_by_count":267},{"id":"1911.11462","title":"G-TAD: Sub-Graph Localization for Temporal Action Detection","created":"2019-11-26","cited_by_count":249},{"id":"2004.13931","title":"Span-based Localizing Network for Natural Language Video Localization","created":"2020-04-29","cited_by_count":235},{"id":"2104.14558","title":"A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning","created":"2021-04-29","cited_by_count":214},{"id":"2004.07514","title":"Local-Global Video-Text Interactions for Temporal Grounding","created":"2020-04-16","cited_by_count":188},{"id":"2004.03545","title":"Dense Regression Network for Video Grounding","created":"2020-04-07","cited_by_count":176},{"id":"1909.04656","title":"Video Representation Learning by Dense Predictive Coding","created":"2019-09-10","cited_by_count":175},{"id":"2004.06130","title":"SpeedNet: Learning the Speediness in Videos","created":"2020-04-13","cited_by_count":171},{"id":"2002.10698","title":"Hierarchical Conditional Relation Networks for Video Question Answering","created":"2020-02-25","cited_by_count":163},{"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":"1910.14303","title":"Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos","created":"2019-10-31","cited_by_count":135},{"id":"1804.05113","title":"Multilevel Language and Vision Integration for Text-to-Clip Retrieval","created":"2018-04-13","cited_by_count":128},{"id":"1710.06236","title":"Single Shot Temporal Action Detection","created":"2017-10-17","cited_by_count":123},{"id":"1708.06734","title":"Representation Learning by Learning to Count","created":"2017-08-22","cited_by_count":120},{"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":"2109.04872","title":"Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding","created":"2021-09-10","cited_by_count":90},{"id":"2103.08109","title":"Boundary Proposal Network for Two-Stage Natural Language Video Localization","created":"2021-03-15","cited_by_count":88},{"id":"1811.08925","title":"MAC: Mining Activity Concepts for Language-based Temporal Localization","created":"2018-11-21","cited_by_count":84},{"id":"1909.05010","title":"Temporally Grounding Language Queries in Videos by Contextual Boundary-aware Prediction","created":"2019-09-11","cited_by_count":84},{"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":"2008.09837","title":"Revisiting Anchor Mechanisms for Temporal Action Localization","created":"2020-08-22","cited_by_count":75},{"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":"2008.00975","title":"SeCo: Exploring Sequence Supervision for Unsupervised Representation Learning","created":"2020-08-03","cited_by_count":65},{"id":"2009.00325","title":"Uncovering Hidden Challenges in Query-Based Video Moment Retrieval","created":"2020-09-01","cited_by_count":58},{"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":"2109.06085","title":"On Pursuit of Designing Multi-modal Transformer for Video Grounding","created":"2021-09-13","cited_by_count":54},{"id":"1709.01362","title":"Predicting Visual Features from Text for Image and Video Caption Retrieval","created":"2017-09-05","cited_by_count":53},{"id":"2007.02503","title":"Tree-Augmented Cross-Modal Encoding for Complex-Query Video Retrieval","created":"2020-07-06","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":"1807.09986","title":"Recurrent Fusion Network for Image Captioning","created":"2018-07-26","cited_by_count":43},{"id":"2209.11572","title":"Multi-Modal Cross-Domain Alignment Network for Video Moment Retrieval","created":"2022-09-23","cited_by_count":43},{"id":"2101.09028","title":"A Closer Look at Temporal Sentence Grounding in Videos: Dataset and Metric","created":"2021-01-22","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":"2108.02722","title":"Video Contrastive Learning with Global Context","created":"2021-08-05","cited_by_count":41},{"id":"2303.07863","title":"You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos","created":"2023-03-14","cited_by_count":41},{"id":"1803.06316","title":"Temporal Gaussian Mixture Layer for Videos","created":"2018-03-16","cited_by_count":40},{"id":"2208.14882","title":"Hierarchical Local-Global Transformer for Temporal Sentence Grounding","created":"2022-08-31","cited_by_count":38},{"id":"1709.06308","title":"Exploring Human-like Attention Supervision in Visual Question Answering","created":"2017-09-19","cited_by_count":36},{"id":"2203.02966","title":"Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding","created":"2022-03-06","cited_by_count":35},{"id":"2207.13457","title":"Reducing the Vision and Language Bias for Temporal Sentence Grounding","created":"2022-07-27","cited_by_count":35},{"id":"2012.02534","title":"F2Net: Learning to Focus on the Foreground for Unsupervised Video Object Segmentation","created":"2020-12-04","cited_by_count":32},{"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":"2201.05307","title":"Unsupervised Temporal Video Grounding with Deep Semantic Clustering","created":"2022-01-14","cited_by_count":30},{"id":"2212.02082","title":"Hierarchical Contrast for Unsupervised Skeleton-based Action Representation Learning","created":"2022-12-05","cited_by_count":30},{"id":"2109.08039","title":"A Survey on Temporal Sentence Grounding in Videos","created":"2021-09-16","cited_by_count":29},{"id":"2301.01871","title":"Hypotheses Tree Building for One-Shot Temporal Sentence Localization","created":"2023-01-05","cited_by_count":25},{"id":"2201.00457","title":"Exploring Motion and Appearance Information for Temporal Sentence Grounding","created":"2022-01-03","cited_by_count":24},{"id":"2207.13450","title":"Skimming, Locating, then Perusing: A Human-Like Framework for Natural Language Video Localization","created":"2022-07-27","cited_by_count":21},{"id":"1904.08141","title":"MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation","created":"2019-04-17","cited_by_count":20},{"id":"2301.00514","title":"Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding","created":"2023-01-02","cited_by_count":19},{"id":"2102.01282","title":"Progressive Localization Networks for Language-based Moment Localization","created":"2021-02-02","cited_by_count":17},{"id":"2110.06058","title":"Multi-Modal Interaction Graph Convolutional Network for Temporal Language Localization in Videos","created":"2021-10-12","cited_by_count":16},{"id":"2010.13386","title":"Video-based Facial Expression Recognition using Graph Convolutional Networks","created":"2020-10-26","cited_by_count":13},{"id":"2012.05499","title":"Spatiotemporal Graph Neural Network based Mask Reconstruction for Video Object Segmentation","created":"2020-12-10","cited_by_count":12},{"id":"2111.04321","title":"Towards Debiasing Temporal Sentence Grounding in Video","created":"2021-11-08","cited_by_count":11},{"id":"2203.05243","title":"A Closer Look at Debiased Temporal Sentence Grounding in Videos: Dataset, Metric, and Approach","created":"2022-03-10","cited_by_count":11},{"id":"2301.05997","title":"Exploiting Auxiliary Caption for Video Grounding","created":"2023-01-15","cited_by_count":10},{"id":"2206.01017","title":"Structured Two-stream Attention Network for Video Question Answering","created":"2022-06-02","cited_by_count":9},{"id":"1906.02182","title":"Two-Stream Region Convolutional 3D Network for Temporal Activity Detection","created":"2019-06-05","cited_by_count":8},{"id":"2111.00417","title":"Hierarchical Deep Residual Reasoning for Temporal Moment Localization","created":"2021-10-31","cited_by_count":4},{"id":"2303.01046","title":"Jointly Visual- and Semantic-Aware Graph Memory Networks for Temporal Sentence Localization in Videos","created":"2023-03-02","cited_by_count":4},{"id":"2207.00744","title":"Gaussian Kernel-based Cross Modal Network for Spatio-Temporal Video Grounding","created":"2022-07-02","cited_by_count":3},{"id":"2302.10813","title":"Tracking Objects and Activities with Attention for Temporal Sentence Grounding","created":"2023-02-21","cited_by_count":2},{"id":"2203.03838","title":"Multi-Scale Self-Contrastive Learning with Hard Negative Mining for Weakly-Supervised Query-based Video Grounding","created":"2022-03-08","cited_by_count":1}],"next_cursor":null}