{"list":"other","total":71,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"id":"1405.4053","title":"Distributed Representations of Sentences and Documents","created":"2014-05-16","cited_by_count":678},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1904.03493","title":"VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research","created":"2019-04-06","cited_by_count":414},{"id":"2001.09099","title":"TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval","created":"2020-01-24","cited_by_count":215},{"id":"1804.00819","title":"End-to-End Dense Video Captioning with Masked Transformer","created":"2018-04-03","cited_by_count":214},{"id":"1501.02530","title":"A Dataset for Movie Description","created":"2015-01-12","cited_by_count":195},{"id":"1605.03705","title":"Movie Description","created":"2016-05-12","cited_by_count":181},{"id":"2107.06912","title":"From Show to Tell: A Survey on Deep Learning-based Image Captioning","created":"2021-07-14","cited_by_count":138},{"id":"1804.09066","title":"ECO: Efficient Convolutional Network for Online Video Understanding","created":"2018-04-24","cited_by_count":115},{"id":"2003.07758","title":"Multi-modal Dense Video Captioning","created":"2020-03-17","cited_by_count":113},{"id":"2003.13942","title":"Spatio-Temporal Graph for Video Captioning with Knowledge Distillation","created":"2020-03-31","cited_by_count":109},{"id":"2002.11566","title":"Object Relational Graph with Teacher-Recommended Learning for Video Captioning","created":"2020-02-26","cited_by_count":107},{"id":"1803.11438","title":"Reconstruction Network for Video Captioning","created":"2018-03-30","cited_by_count":98},{"id":"2011.11760","title":"Multimodal Pretraining for Dense Video Captioning","created":"2020-11-10","cited_by_count":79},{"id":"1701.03126","title":"Attention-Based Multimodal Fusion for Video Description","created":"2017-01-11","cited_by_count":75},{"id":"1804.00100","title":"Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning","created":"2018-03-31","cited_by_count":68},{"id":"1905.03966","title":"Memory-Attended Recurrent Network for Video Captioning","created":"2019-05-10","cited_by_count":65},{"id":"1610.02947","title":"End-to-end Concept Word Detection for Video Captioning, Retrieval, and Question Answering","created":"2016-10-10","cited_by_count":60},{"id":"1804.08274","title":"Jointly Localizing and Describing Events for Dense Video Captioning","created":"2018-04-23","cited_by_count":60},{"id":"1902.10322","title":"Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning","created":"2019-02-27","cited_by_count":60},{"id":"1904.03870","title":"Streamlined Dense Video Captioning","created":"2019-04-08","cited_by_count":57},{"id":"1510.07712","title":"Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks","created":"2015-10-26","cited_by_count":54},{"id":"1505.01861","title":"Jointly Modeling Embedding and Translation to Bridge Video and Language","created":"2015-05-07","cited_by_count":53},{"id":"1803.01457","title":"Less Is More: Picking Informative Frames for Video Captioning","created":"2018-03-05","cited_by_count":52},{"id":"1611.08002","title":"Semantic Compositional Networks for Visual Captioning","created":"2016-11-23","cited_by_count":50},{"id":"1908.10072","title":"Controllable Video Captioning with POS Sequence Guidance Based on Gated Fusion Network","created":"2019-08-27","cited_by_count":48},{"id":"1711.11135","title":"Video Captioning via Hierarchical Reinforcement Learning","created":"2017-11-29","cited_by_count":47},{"id":"1611.07675","title":"Video Captioning with Transferred Semantic Attributes","created":"2016-11-23","cited_by_count":46},{"id":"1403.6173","title":"Coherent Multi-Sentence Video Description with Variable Level of Detail","created":"2014-03-24","cited_by_count":45},{"id":"1906.04375","title":"Object-aware Aggregation with Bidirectional Temporal Graph for Video Captioning","created":"2019-06-11","cited_by_count":42},{"id":"1502.06648","title":"Recognizing Fine-Grained and Composite Activities using Hand-Centric Features and Script Data","created":"2015-02-23","cited_by_count":40},{"id":"1807.10018","title":"Move Forward and Tell: A Progressive Generator of Video Descriptions","created":"2018-07-26","cited_by_count":35},{"id":"2102.00831","title":"Semantic Grouping Network for Video Captioning","created":"2021-02-01","cited_by_count":34},{"id":"1503.01070","title":"Using Descriptive Video Services to Create a Large Data Source for Video Annotation Research","created":"2015-03-03","cited_by_count":33},{"id":"1511.03476","title":"Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning","created":"2015-11-11","cited_by_count":30},{"id":"1611.05592","title":"Multimodal Memory Modelling for Video Captioning","created":"2016-11-17","cited_by_count":20},{"id":"1611.09312","title":"Hierarchical Boundary-Aware Neural Encoder for Video Captioning","created":"2016-11-28","cited_by_count":20},{"id":"2007.09049","title":"Learning to Discretely Compose Reasoning Module Networks for Video Captioning","created":"2020-07-17","cited_by_count":20},{"id":"1706.01231","title":"Hierarchical LSTM with Adjusted Temporal Attention for Video Captioning","created":"2017-06-05","cited_by_count":19},{"id":"1704.01502","title":"Weakly Supervised Dense Video Captioning","created":"2017-04-05","cited_by_count":18},{"id":"1707.06029","title":"Supervising Neural Attention Models for Video Captioning by Human Gaze Data","created":"2017-07-19","cited_by_count":18},{"id":"1812.11004","title":"Hierarchical LSTMs with Adaptive Attention for Visual Captioning","created":"2018-12-26","cited_by_count":18},{"id":"2112.07515","title":"CoCo-BERT: Improving Video-Language Pre-training with Contrastive Cross-modal Matching and Denoising","created":"2021-12-14","cited_by_count":18},{"id":"1704.07489","title":"Multi-Task Video Captioning with Video and Entailment Generation","created":"2017-04-24","cited_by_count":17},{"id":"1708.09667","title":"Video Captioning with Guidance of Multimodal Latent Topics","created":"2017-08-31","cited_by_count":16},{"id":"1703.04096","title":"Improving Interpretability of Deep Neural Networks with Semantic Information","created":"2017-03-12","cited_by_count":15},{"id":"1708.02478","title":"From Deterministic to Generative: Multi-Modal Stochastic RNNs for Video Captioning","created":"2017-08-08","cited_by_count":15},{"id":"1905.01077","title":"Temporal Deformable Convolutional Encoder-Decoder Networks for Video Captioning","created":"2019-05-03","cited_by_count":15},{"id":"1806.00186","title":"Video Description: A Survey of Methods, Datasets and Evaluation Metrics","created":"2018-06-01","cited_by_count":13},{"id":"1906.01452","title":"Reconstruct and Represent Video Contents for Captioning via Reinforcement Learning","created":"2019-06-03","cited_by_count":12},{"id":"1604.01729","title":"Improving LSTM-based Video Description with Linguistic Knowledge Mined from Text","created":"2016-04-06","cited_by_count":11},{"id":"1612.00234","title":"Video Captioning with Multi-Faceted Attention","created":"2016-12-01","cited_by_count":10},{"id":"1803.07950","title":"End-to-End Video Captioning with Multitask Reinforcement Learning","created":"2018-03-21","cited_by_count":10},{"id":"1907.12905","title":"Watch It Twice: Video Captioning with a Refocused Video Encoder","created":"2019-07-21","cited_by_count":9},{"id":"2112.01073","title":"Controllable Video Captioning with an Exemplar Sentence","created":"2021-12-02","cited_by_count":9},{"id":"1610.04997","title":"Spatio-Temporal Attention Models for Grounded Video Captioning","created":"2016-10-17","cited_by_count":8},{"id":"2108.03662","title":"Discriminative Latent Semantic Graph for Video Captioning","created":"2021-08-08","cited_by_count":7},{"id":"1608.04959","title":"Frame- and Segment-Level Features and Candidate Pool Evaluation for Video Caption Generation","created":"2016-08-17","cited_by_count":5},{"id":"1611.09053","title":"Bidirectional Multirate Reconstruction for Temporal Modeling in Videos","created":"2016-11-28","cited_by_count":5},{"id":"1712.09532","title":"Consensus-based Sequence Training for Video Captioning","created":"2017-12-27","cited_by_count":5},{"id":"1605.05440","title":"Beyond Caption To Narrative: Video Captioning With Multiple Sentences","created":"2016-05-18","cited_by_count":4},{"id":"1807.03658","title":"Video Captioning with Boundary-aware Hierarchical Language Decoding and Joint Video Prediction","created":"2018-07-08","cited_by_count":4},{"id":"1911.01857","title":"Video Captioning with Text-based Dynamic Attention and Step-by-Step Learning","created":"2019-11-05","cited_by_count":2},{"id":"1611.06492","title":"Recurrent Memory Addressing for describing videos","created":"2016-11-20","cited_by_count":1},{"id":"2202.10828","title":"Exploiting long-term temporal dynamics for video captioning","created":"2022-02-22","cited_by_count":1}],"next_cursor":null}