{"list":"other","total":91,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1801.07829","title":"Dynamic Graph CNN for Learning on Point Clouds","created":"2018-01-24","cited_by_count":2223},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1704.04368","title":"Get To The Point: Summarization with Pointer-Generator Networks","created":"2017-04-14","cited_by_count":1292},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"1506.03340","title":"Teaching Machines to Read and Comprehend","created":"2015-06-10","cited_by_count":1049},{"id":"1508.04025","title":"Effective Approaches to Attention-based Neural Machine Translation","created":"2015-08-17","cited_by_count":1026},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"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":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"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":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"1911.00359","title":"CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data","created":"2019-11-01","cited_by_count":548},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"1509.00685","title":"A Neural Attention Model for Abstractive Sentence Summarization","created":"2015-09-02","cited_by_count":396},{"id":"1312.3005","title":"One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling","created":"2013-12-11","cited_by_count":308},{"id":"2004.14373","title":"ToTTo: A Controlled Table-To-Text Generation Dataset","created":"2020-04-29","cited_by_count":268},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263},{"id":"1603.03925","title":"Image Captioning with Semantic Attention","created":"2016-03-12","cited_by_count":260},{"id":"1912.06992","title":"Action Genome: Actions as Composition of Spatio-temporal Scene Graphs","created":"2019-12-15","cited_by_count":250},{"id":"1707.08052","title":"Challenges in Data-to-Document Generation","created":"2017-07-25","cited_by_count":226},{"id":"1603.06393","title":"Incorporating Copying Mechanism in Sequence-to-Sequence Learning","created":"2016-03-21","cited_by_count":218},{"id":"1804.00819","title":"End-to-End Dense Video Captioning with Masked Transformer","created":"2018-04-03","cited_by_count":214},{"id":"1810.04020","title":"A Comprehensive Survey of Deep Learning for Image Captioning","created":"2018-10-06","cited_by_count":214},{"id":"1501.02530","title":"A Dataset for Movie Description","created":"2015-01-12","cited_by_count":195},{"id":"1808.10792","title":"Bottom-Up Abstractive Summarization","created":"2018-08-31","cited_by_count":177},{"id":"2010.04389","title":"A Survey of Knowledge-Enhanced Text Generation","created":"2020-10-09","cited_by_count":120},{"id":"1603.07252","title":"Neural Summarization by Extracting Sentences and Words","created":"2016-03-23","cited_by_count":116},{"id":"2008.02457","title":"Graph Convolutional Networks for Hyperspectral Image Classification","created":"2020-08-06","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":"2006.16673","title":"Cross-Scale Internal Graph Neural Network for Image Super-Resolution","created":"2020-06-30","cited_by_count":94},{"id":"1903.10658","title":"Unpaired Image Captioning via Scene Graph Alignments","created":"2019-03-26","cited_by_count":82},{"id":"1706.00359","title":"Discovering Discrete Latent Topics with Neural Variational Inference","created":"2017-06-01","cited_by_count":79},{"id":"2005.05402","title":"MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning","created":"2020-05-11","cited_by_count":79},{"id":"1811.10652","title":"Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions","created":"2018-11-26","cited_by_count":65},{"id":"1807.02305","title":"Neural Document Summarization by Jointly Learning to Score and Select Sentences","created":"2018-07-06","cited_by_count":56},{"id":"1711.09724","title":"Table-to-text Generation by Structure-aware Seq2seq Learning","created":"2017-11-27","cited_by_count":54},{"id":"1803.10357","title":"Deep Communicating Agents for Abstractive Summarization","created":"2018-03-27","cited_by_count":50},{"id":"2011.10132","title":"VLG-Net: Video-Language Graph Matching Network for Video Grounding","created":"2020-11-19","cited_by_count":50},{"id":"2005.00969","title":"Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraints","created":"2020-05-03","cited_by_count":48},{"id":"1403.6173","title":"Coherent Multi-Sentence Video Description with Variable Level of Detail","created":"2014-03-24","cited_by_count":45},{"id":"1906.03221","title":"Data-to-text Generation with Entity Modeling","created":"2019-06-07","cited_by_count":45},{"id":"1603.08148","title":"Pointing the Unknown Words","created":"2016-03-26","cited_by_count":43},{"id":"1906.04375","title":"Object-aware Aggregation with Bidirectional Temporal Graph for Video Captioning","created":"2019-06-11","cited_by_count":42},{"id":"1805.11234","title":"Table-to-Text: Describing Table Region with Natural Language","created":"2018-05-29","cited_by_count":41},{"id":"2102.02810","title":"Controlling Hallucinations at Word Level in Data-to-Text Generation","created":"2021-02-04","cited_by_count":41},{"id":"2005.04308","title":"Building a PubMed knowledge graph","created":"2020-05-08","cited_by_count":38},{"id":"2103.15662","title":"Unified Graph Structured Models for Video Understanding","created":"2021-03-29","cited_by_count":38},{"id":"1808.00661","title":"Adaptive Temporal Encoding Network for Video Instance-level Human Parsing","created":"2018-08-02","cited_by_count":36},{"id":"2007.09580","title":"Length-Controllable Image Captioning","created":"2020-07-19","cited_by_count":36},{"id":"1607.00970","title":"Sequence to Backward and Forward Sequences: A Content-Introducing Approach to Generative Short-Text Conversation","created":"2016-07-04","cited_by_count":35},{"id":"1804.09235","title":"On the effectiveness of task granularity for transfer learning","created":"2018-04-24","cited_by_count":35},{"id":"1603.08887","title":"Learning-Based Single-Document Summarization with Compression and Anaphoricity Constraints","created":"2016-03-29","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":"1907.08448","title":"Deep Graph-Convolutional Image Denoising","created":"2019-07-19","cited_by_count":32},{"id":"2204.08121","title":"End-to-end Dense Video Captioning as Sequence Generation","created":"2022-04-18","cited_by_count":27},{"id":"1504.06063","title":"Multimodal Convolutional Neural Networks for Matching Image and Sentence","created":"2015-04-23","cited_by_count":25},{"id":"1908.09995","title":"Temporal Reasoning Graph for Activity Recognition","created":"2019-08-27","cited_by_count":22},{"id":"2105.14778","title":"Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation","created":"2021-05-31","cited_by_count":21},{"id":"2108.12516","title":"Few-Shot Table-to-Text Generation with Prototype Memory","created":"2021-08-27","cited_by_count":21},{"id":"1709.00155","title":"Order-Planning Neural Text Generation From Structured Data","created":"2017-09-01","cited_by_count":20},{"id":"1908.03067","title":"Key Fact as Pivot: A Two-Stage Model for Low Resource Table-to-Text Generation","created":"2019-08-08","cited_by_count":20},{"id":"1909.11953","title":"Hyperspectral Image Classification With Context-Aware Dynamic Graph Convolutional Network","created":"2019-09-26","cited_by_count":20},{"id":"1809.01797","title":"Describing a Knowledge Base","created":"2018-09-06","cited_by_count":18},{"id":"1909.02304","title":"Table-to-Text Generation with Effective Hierarchical Encoder on Three Dimensions (Row, Column and Time)","created":"2019-09-05","cited_by_count":18},{"id":"2010.02744","title":"Stepwise Extractive Summarization and Planning with Structured Transformers","created":"2020-10-06","cited_by_count":16},{"id":"2109.13499","title":"Modelling Neighbor Relation in Joint Space-Time Graph for Video Correspondence Learning","created":"2021-09-28","cited_by_count":16},{"id":"1410.1090","title":"Explain Images with Multimodal Recurrent Neural Networks","created":"2014-10-04","cited_by_count":15},{"id":"1609.07479","title":"Incorporating Relation Paths in Neural Relation Extraction","created":"2016-09-23","cited_by_count":9},{"id":"1704.04530","title":"Neural Extractive Summarization with Side Information","created":"2017-04-14","cited_by_count":6},{"id":"1509.06658","title":"Attribute-Graph: A Graph based approach to Image Ranking","created":"2015-09-22","cited_by_count":2},{"id":"2009.08899","title":"Image Captioning with Attention for Smart Local Tourism using EfficientNet","created":"2020-09-18","cited_by_count":2},{"id":"2103.11118","title":"Keywords Guided Method Name Generation","created":"2021-03-20","cited_by_count":2},{"id":"1412.8419","title":"Simple Image Description Generator via a Linear Phrase-Based Approach","created":"2014-12-29","cited_by_count":1}],"next_cursor":null}