{"list":"other","total":52,"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"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":"1703.03130","title":"A Structured Self-attentive Sentence Embedding","created":"2017-03-09","cited_by_count":318},{"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":"2001.09099","title":"TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval","created":"2020-01-24","cited_by_count":215},{"id":"2004.07514","title":"Local-Global Video-Text Interactions for Temporal Grounding","created":"2020-04-16","cited_by_count":188},{"id":"2108.06428","title":"FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration","created":"2021-08-13","cited_by_count":169},{"id":"2103.11555","title":"Context-aware Biaffine Localizing Network for Temporal Sentence Grounding","created":"2021-03-22","cited_by_count":107},{"id":"1807.07428","title":"Modeling Visual Context is Key to Augmenting Object Detection Datasets","created":"2018-07-19","cited_by_count":106},{"id":"1904.03282","title":"Weakly Supervised Video Moment Retrieval From Text Queries","created":"2019-04-05","cited_by_count":85},{"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":"1906.02549","title":"Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video","created":"2019-06-06","cited_by_count":60},{"id":"2201.00454","title":"Memory-Guided Semantic Learning Network for Temporal Sentence Grounding","created":"2022-01-03","cited_by_count":46},{"id":"2209.11572","title":"Multi-Modal Cross-Domain Alignment Network for Video Moment Retrieval","created":"2022-09-23","cited_by_count":43},{"id":"2109.06398","title":"Adaptive Proposal Generation Network for Temporal Sentence Localization in Videos","created":"2021-09-14","cited_by_count":42},{"id":"2008.10238","title":"VLANet: Video-Language Alignment Network for Weakly-Supervised Video Moment Retrieval","created":"2020-08-24","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":"1909.13784","title":"LoGAN: Latent Graph Co-Attention Network for Weakly-Supervised Video Moment Retrieval","created":"2019-09-27","cited_by_count":40},{"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":"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":"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":"2011.10254","title":"Unbalanced Incomplete Multi-view Clustering via the Scheme of View Evolution: Weak Views are Meat; Strong Views do Eat","created":"2020-11-20","cited_by_count":30},{"id":"2011.10331","title":"ANIMC: A Soft Framework for Auto-weighted Noisy and Incomplete Multi-view Clustering","created":"2020-11-20","cited_by_count":30},{"id":"2201.05307","title":"Unsupervised Temporal Video Grounding with Deep Semantic Clustering","created":"2022-01-14","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":"2009.10434","title":"Frame-wise Cross-modal Matching for Video Moment Retrieval","created":"2020-09-22","cited_by_count":26},{"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":"2304.01563","title":"Attribute-Consistent Knowledge Graph Representation Learning for Multi-Modal Entity Alignment","created":"2023-04-04","cited_by_count":24},{"id":"2008.08257","title":"Regularized Two-Branch Proposal Networks for Weakly-Supervised Moment Retrieval in Videos","created":"2020-08-19","cited_by_count":23},{"id":"2009.08614","title":"Reinforcement Learning for Weakly Supervised Temporal Grounding of Natural Language in Untrimmed Videos","created":"2020-09-18","cited_by_count":23},{"id":"2011.10396","title":"Double Self-weighted Multi-view Clustering via Adaptive View Fusion","created":"2020-11-20","cited_by_count":23},{"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":"2412.06284","title":"Your Data Is Not Perfect: Towards Cross-Domain Out-of-Distribution Detection in Class-Imbalanced Data","created":"2024-12-09","cited_by_count":21},{"id":"2412.15678","title":"Multi-Pair Temporal Sentence Grounding via Multi-Thread Knowledge Transfer Network","created":"2024-12-20","cited_by_count":15},{"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":"2106.12384","title":"Reinforcement Learning-based Dialogue Guided Event Extraction to Exploit Argument Relations","created":"2021-06-23","cited_by_count":10},{"id":"2605.26441","title":"Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspective","created":"2026-05-26","cited_by_count":8},{"id":"2306.11020","title":"Dual-Gated Fusion with Prefix-Tuning for Multi-Modal Relation Extraction","created":"2023-06-19","cited_by_count":7},{"id":"2605.29812","title":"Not All Inputs Are Valid: Towards Open-Set Video Moment Retrieval Using Language","created":"2026-05-28","cited_by_count":6},{"id":"2605.29793","title":"Fewer Steps, Better Performance: Efficient Cross-Modal Clip Trimming for Video Moment Retrieval Using Language","created":"2026-05-28","cited_by_count":5}],"next_cursor":null}