{"list":"other","total":66,"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":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802},{"id":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"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":"2210.07242","title":"OpenOOD: Benchmarking Generalized Out-of-Distribution Detection","created":"2022-10-13","cited_by_count":268},{"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":"2004.03545","title":"Dense Regression Network for Video Grounding","created":"2020-04-07","cited_by_count":176},{"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":"1910.14303","title":"Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos","created":"2019-10-31","cited_by_count":135},{"id":"2001.09691","title":"Multi-Modal Domain Adaptation for Fine-Grained Action Recognition","created":"2020-01-27","cited_by_count":115},{"id":"2207.11247","title":"Panoptic Scene Graph Generation","created":"2022-07-22","cited_by_count":114},{"id":"2103.11555","title":"Context-aware Biaffine Localizing Network for Temporal Sentence Grounding","created":"2021-03-22","cited_by_count":107},{"id":"2108.11941","title":"Semantically Coherent Out-of-Distribution Detection","created":"2021-08-26","cited_by_count":107},{"id":"1712.00636","title":"Compressed Video Action Recognition","created":"2017-12-02","cited_by_count":106},{"id":"2203.16434","title":"TubeDETR: Spatio-Temporal Video Grounding with Transformers","created":"2022-03-30","cited_by_count":98},{"id":"2109.04872","title":"Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding","created":"2021-09-10","cited_by_count":90},{"id":"1904.03282","title":"Weakly Supervised Video Moment Retrieval From Text Queries","created":"2019-04-05","cited_by_count":85},{"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":"2204.05306","title":"Full-Spectrum Out-of-Distribution Detection","created":"2022-04-11","cited_by_count":63},{"id":"1906.02549","title":"Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video","created":"2019-06-06","cited_by_count":60},{"id":"1812.03849","title":"Weakly Supervised Dense Event Captioning in Videos","created":"2018-12-10","cited_by_count":58},{"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":"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":"1909.13784","title":"LoGAN: Latent Graph Co-Attention Network for Weakly-Supervised Video Moment Retrieval","created":"2019-09-27","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":"2106.16136","title":"Weakly Supervised Temporal Adjacent Network for Language Grounding","created":"2021-06-30","cited_by_count":37},{"id":"1901.03460","title":"DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition","created":"2019-01-11","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":"1811.11057","title":"Fast Object Detection in Compressed Video","created":"2018-11-27","cited_by_count":33},{"id":"1906.10057","title":"Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compression","created":"2019-06-24","cited_by_count":33},{"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":"2110.05717","title":"Relation-aware Video Reading Comprehension for Temporal Language Grounding","created":"2021-10-12","cited_by_count":27},{"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":"2008.08257","title":"Regularized Two-Branch Proposal Networks for Weakly-Supervised Moment Retrieval in Videos","created":"2020-08-19","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":"1904.08141","title":"MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation","created":"2019-04-17","cited_by_count":20},{"id":"2208.02998","title":"Localized Sparse Incomplete Multi-view Clustering","created":"2022-08-05","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":"2203.15336","title":"End-to-End Compressed Video Representation Learning for Generic Event Boundary Detection","created":"2022-03-29","cited_by_count":16},{"id":"2012.05499","title":"Spatiotemporal Graph Neural Network based Mask Reconstruction for Video Object Segmentation","created":"2020-12-10","cited_by_count":12},{"id":"2107.12192","title":"Accelerating Video Object Segmentation with Compressed Video","created":"2021-07-26","cited_by_count":10},{"id":"1810.00661","title":"Enhancing Geometric Deep Learning via Graph Filter Deconvolution","created":"2018-09-24","cited_by_count":4},{"id":"2010.05864","title":"Webly Supervised Image Classification with Metadata: Automatic Noisy Label Correction via Visual-Semantic Graph","created":"2020-10-12","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":"1611.10252","title":"SeDMiD for Confusion Detection: Uncovering Mind State from Time Series Brain Wave Data","created":"2016-11-29","cited_by_count":2}],"next_cursor":null}