{"list":"other","total":130,"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"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":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1411.1792","title":"How transferable are features in deep neural networks?","created":"2014-11-06","cited_by_count":1225},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"1405.4053","title":"Distributed Representations of Sentences and Documents","created":"2014-05-16","cited_by_count":678},{"id":"1303.5778","title":"Speech Recognition with Deep Recurrent Neural Networks","created":"2013-03-22","cited_by_count":669},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"1511.06732","title":"Sequence Level Training with Recurrent Neural Networks","created":"2015-11-20","cited_by_count":576},{"id":"1711.09577","title":"Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?","created":"2017-11-27","cited_by_count":551},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"1912.06430","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","created":"2019-12-13","cited_by_count":507},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"1502.04681","title":"Unsupervised Learning of Video Representations using LSTMs","created":"2015-02-16","cited_by_count":435},{"id":"1310.1531","title":"DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition","created":"2013-10-06","cited_by_count":424},{"id":"1605.06409","title":"R-FCN: Object Detection via Region-based Fully Convolutional Networks","created":"2016-05-20","cited_by_count":414},{"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":"1512.02902","title":"MovieQA: Understanding Stories in Movies through Question-Answering","created":"2015-12-09","cited_by_count":304},{"id":"1912.02315","title":"12-in-1: Multi-Task Vision and Language Representation Learning","created":"2019-12-05","cited_by_count":278},{"id":"2006.14799","title":"Evaluation of Text Generation: A Survey","created":"2020-06-26","cited_by_count":277},{"id":"1903.07593","title":"Learning Correspondence from the Cycle-Consistency of Time","created":"2019-03-18","cited_by_count":269},{"id":"1806.11230","title":"Human Action Recognition and Prediction: A Survey","created":"2018-06-28","cited_by_count":227},{"id":"1312.6229","title":"OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks","created":"2013-12-21","cited_by_count":224},{"id":"1804.00819","title":"End-to-End Dense Video Captioning with Masked Transformer","created":"2018-04-03","cited_by_count":214},{"id":"1703.09902","title":"Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation","created":"2017-03-29","cited_by_count":206},{"id":"1711.07837","title":"UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss","created":"2017-11-21","cited_by_count":202},{"id":"1411.2539","title":"Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models","created":"2014-11-10","cited_by_count":198},{"id":"1501.02530","title":"A Dataset for Movie Description","created":"2015-01-12","cited_by_count":195},{"id":"2003.00392","title":"Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning","created":"2020-03-01","cited_by_count":180},{"id":"1505.00487","title":"Sequence to Sequence -- Video to Text","created":"2015-05-03","cited_by_count":158},{"id":"1710.00421","title":"Video Generation From Text","created":"2017-10-01","cited_by_count":154},{"id":"1904.07846","title":"Temporal Cycle-Consistency Learning","created":"2019-04-16","cited_by_count":154},{"id":"1604.02748","title":"TGIF: A New Dataset and Benchmark on Animated GIF Description","created":"2016-04-10","cited_by_count":124},{"id":"1804.09066","title":"ECO: Efficient Convolutional Network for Online Video Understanding","created":"2018-04-24","cited_by_count":115},{"id":"1411.4952","title":"From Captions to Visual Concepts and Back","created":"2014-11-18","cited_by_count":109},{"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":"1902.05660","title":"Cycle-Consistency for Robust Visual Question Answering","created":"2019-02-15","cited_by_count":105},{"id":"1804.02516","title":"Learning a Text-Video Embedding from Incomplete and Heterogeneous Data","created":"2018-04-07","cited_by_count":103},{"id":"1804.09627","title":"Actor and Observer: Joint Modeling of First and Third-Person Videos","created":"2018-04-25","cited_by_count":103},{"id":"1810.07212","title":"Cross-Modal and Hierarchical Modeling of Video and Text","created":"2018-10-16","cited_by_count":103},{"id":"1908.03477","title":"Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings","created":"2019-08-09","cited_by_count":101},{"id":"2011.00597","title":"COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning","created":"2020-11-01","cited_by_count":100},{"id":"1803.11438","title":"Reconstruction Network for Video Captioning","created":"2018-03-30","cited_by_count":98},{"id":"1412.4729","title":"Translating Videos to Natural Language Using Deep Recurrent Neural Networks","created":"2014-12-15","cited_by_count":95},{"id":"1412.6632","title":"Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)","created":"2014-12-20","cited_by_count":94},{"id":"1502.08029","title":"Describing Videos by Exploiting Temporal Structure","created":"2015-02-27","cited_by_count":88},{"id":"1809.06181","title":"Dual Encoding for Zero-Example Video Retrieval","created":"2018-09-17","cited_by_count":85},{"id":"1604.04494","title":"Long-term Temporal Convolutions for Action Recognition","created":"2016-04-15","cited_by_count":84},{"id":"2005.05402","title":"MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning","created":"2020-05-11","cited_by_count":79},{"id":"1812.06587","title":"Grounded Video Description","created":"2018-12-17","cited_by_count":78},{"id":"1804.00100","title":"Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning","created":"2018-03-31","cited_by_count":68},{"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":"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":"1805.12589","title":"Fast, Diverse and Accurate Image Captioning Guided By Part-of-Speech","created":"2018-05-31","cited_by_count":55},{"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":"1709.01362","title":"Predicting Visual Features from Text for Image and Video Caption Retrieval","created":"2017-09-05","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":"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":"1804.09235","title":"On the effectiveness of task granularity for transfer learning","created":"2018-04-24","cited_by_count":35},{"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":"1505.06027","title":"Weakly-Supervised Alignment of Video With Text","created":"2015-05-22","cited_by_count":21},{"id":"1708.02300","title":"Reinforced Video Captioning with Entailment Rewards","created":"2017-08-07","cited_by_count":21},{"id":"1804.05448","title":"Watch, Listen, and Describe: Globally and Locally Aligned Cross-Modal Attentions for Video Captioning","created":"2018-04-15","cited_by_count":21},{"id":"1506.01698","title":"The Long-Short Story of Movie Description","created":"2015-06-04","cited_by_count":20},{"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}],"next_cursor":"100"}