{"list":"other","total":70,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"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":"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":"2307.16715","title":"UniVTG: Towards Unified Video-Language Temporal Grounding","created":"2023-07-31","cited_by_count":190},{"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":"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":"2103.11555","title":"Context-aware Biaffine Localizing Network for Temporal Sentence Grounding","created":"2021-03-22","cited_by_count":107},{"id":"1904.03282","title":"Weakly Supervised Video Moment Retrieval From Text Queries","created":"2019-04-05","cited_by_count":85},{"id":"1909.05010","title":"Temporally Grounding Language Queries in Videos by Contextual Boundary-aware Prediction","created":"2019-09-11","cited_by_count":84},{"id":"1809.01337","title":"Localizing Moments in Video with Temporal Language","created":"2018-09-05","cited_by_count":83},{"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":"2208.02515","title":"Fine-Grained Semantically Aligned Vision-Language Pre-Training","created":"2022-08-04","cited_by_count":68},{"id":"1709.01362","title":"Predicting Visual Features from Text for Image and Video Caption Retrieval","created":"2017-09-05","cited_by_count":53},{"id":"2403.05234","title":"Benchmarking Micro-action Recognition: Dataset, Methods, and Applications","created":"2024-03-08","cited_by_count":48},{"id":"2303.14369","title":"Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning","created":"2023-03-25","cited_by_count":45},{"id":"2209.11572","title":"Multi-Modal Cross-Domain Alignment Network for Video Moment Retrieval","created":"2022-09-23","cited_by_count":43},{"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":"2208.14882","title":"Hierarchical Local-Global Transformer for Temporal Sentence Grounding","created":"2022-08-31","cited_by_count":38},{"id":"2106.16136","title":"Weakly Supervised Temporal Adjacent Network for Language Grounding","created":"2021-06-30","cited_by_count":37},{"id":"1909.00239","title":"WSLLN: Weakly Supervised Natural Language Localization Networks","created":"2019-08-31","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":"2201.09168","title":"Reading-strategy Inspired Visual Representation Learning for Text-to-Video Retrieval","created":"2022-01-23","cited_by_count":34},{"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":"2208.08040","title":"A Survey on Incomplete Multi-view Clustering","created":"2022-08-17","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":"2212.02082","title":"Hierarchical Contrast for Unsupervised Skeleton-based Action Representation Learning","created":"2022-12-05","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":"2301.01871","title":"Hypotheses Tree Building for One-Shot Temporal Sentence Localization","created":"2023-01-05","cited_by_count":25},{"id":"2311.02608","title":"Deep Learning-based 3D Point Cloud Classification: A Systematic Survey and Outlook","created":"2023-11-05","cited_by_count":24},{"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":"2307.14277","title":"G2L: Semantically Aligned and Uniform Video Grounding via Geodesic and Game Theory","created":"2023-07-26","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":"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":"2303.07180","title":"Incomplete Multi-View Multi-Label Learning via Label-Guided Masked View- and Category-Aware Transformers","created":"2023-03-13","cited_by_count":17},{"id":"2304.00429","title":"Information Recovery-Driven Deep Incomplete Multiview Clustering Network","created":"2023-04-02","cited_by_count":16},{"id":"2412.15678","title":"Multi-Pair Temporal Sentence Grounding via Multi-Thread Knowledge Transfer Network","created":"2024-12-20","cited_by_count":15},{"id":"1402.0567","title":"Efficient Computation of the Shapley Value for Game-Theoretic Network Centrality","created":"2014-02-04","cited_by_count":14},{"id":"2504.02454","title":"Taylor Series-Inspired Local Structure Fitting Network for Few-shot Point Cloud Semantic Segmentation","created":"2025-04-03","cited_by_count":14},{"id":"2511.12121","title":"To Align or Not to Align: Strategic Multimodal Representation Alignment for Optimal Performance","created":"2025-11-15","cited_by_count":14},{"id":"2303.08358","title":"DICNet: Deep Instance-Level Contrastive Network for Double Incomplete Multi-View Multi-Label Classification","created":"2023-03-15","cited_by_count":13},{"id":"2311.00603","title":"Occluded Person Re-Identification with Deep Learning: A Survey and Perspectives","created":"2023-11-01","cited_by_count":13},{"id":"2409.09953","title":"Uncertainty-Guided Appearance-Motion Association Network for Out-of-Distribution Action Detection","created":"2024-09-16","cited_by_count":12},{"id":"2508.04022","title":"Prototype-Driven Structure Synergy Network for Remote Sensing Images Segmentation","created":"2025-08-06","cited_by_count":11},{"id":"2305.10260","title":"From Region to Patch: Attribute-Aware Foreground-Background Contrastive Learning for Fine-Grained Fashion Retrieval","created":"2023-05-17","cited_by_count":9},{"id":"2412.15668","title":"Adaptive Hierarchical Graph Cut for Multi-granularity Out-of-distribution Detection","created":"2024-12-20","cited_by_count":8},{"id":"2506.17633","title":"Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detection","created":"2025-06-21","cited_by_count":8},{"id":"2504.03342","title":"EOOD: Entropy-based Out-of-distribution Detection","created":"2025-04-04","cited_by_count":5},{"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":"2305.04123","title":"Transform-Equivariant Consistency Learning for Temporal Sentence Grounding","created":"2023-05-06","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}],"next_cursor":null}