{"list":"other","total":59,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"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":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"id":"1704.04368","title":"Get To The Point: Summarization with Pointer-Generator Networks","created":"2017-04-14","cited_by_count":1292},{"id":"1912.08777","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","created":"2019-12-18","cited_by_count":1102},{"id":"2005.00661","title":"On Faithfulness and Factuality in Abstractive Summarization","created":"2020-05-02","cited_by_count":900},{"id":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"1910.12840","title":"Evaluating the Factual Consistency of Abstractive Text Summarization","created":"2019-10-28","cited_by_count":584},{"id":"1705.08045","title":"Learning multiple visual domains with residual adapters","created":"2017-05-22","cited_by_count":557},{"id":"1908.08345","title":"Text Summarization with Pretrained Encoders","created":"2019-08-22","cited_by_count":556},{"id":"1911.12237","title":"SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","created":"2019-11-27","cited_by_count":535},{"id":"1705.04304","title":"A Deep Reinforced Model for Abstractive Summarization","created":"2017-05-11","cited_by_count":365},{"id":"2104.05938","title":"QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization","created":"2021-04-13","cited_by_count":365},{"id":"2005.00200","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","created":"2020-05-01","cited_by_count":362},{"id":"2112.06825","title":"VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks","created":"2021-12-13","cited_by_count":320},{"id":"2002.06353","title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation","created":"2020-02-15","cited_by_count":259},{"id":"2002.11296","title":"Sparse Sinkhorn Attention","created":"2020-02-26","cited_by_count":251},{"id":"2001.09099","title":"TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval","created":"2020-01-24","cited_by_count":215},{"id":"1605.03705","title":"Movie Description","created":"2016-05-12","cited_by_count":181},{"id":"1808.10792","title":"Bottom-Up Abstractive Summarization","created":"2018-08-31","cited_by_count":177},{"id":"2201.03533","title":"SCROLLS: Standardized CompaRison Over Long Language Sequences","created":"2022-01-10","cited_by_count":170},{"id":"1811.00347","title":"How2: A Large-scale Dataset for Multimodal Language Understanding","created":"2018-11-01","cited_by_count":138},{"id":"1905.13164","title":"Hierarchical Transformers for Multi-Document Summarization","created":"2019-05-30","cited_by_count":132},{"id":"2104.08202","title":"$Q^{2}$: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering","created":"2021-04-16","cited_by_count":132},{"id":"2205.12854","title":"Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectors","created":"2022-05-25","cited_by_count":104},{"id":"2105.09996","title":"VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding","created":"2021-05-20","cited_by_count":102},{"id":"2106.04632","title":"VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation","created":"2021-06-08","cited_by_count":95},{"id":"2005.05402","title":"MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning","created":"2020-05-11","cited_by_count":79},{"id":"2104.07091","title":"SummScreen: A Dataset for Abstractive Screenplay Summarization","created":"2021-04-14","cited_by_count":79},{"id":"2109.02492","title":"DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization","created":"2021-09-06","cited_by_count":72},{"id":"2110.10150","title":"Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents","created":"2021-10-16","cited_by_count":65},{"id":"1403.6173","title":"Coherent Multi-Sentence Video Description with Variable Level of Detail","created":"2014-03-24","cited_by_count":45},{"id":"1906.07901","title":"Multimodal Abstractive Summarization for How2 Videos","created":"2019-06-19","cited_by_count":41},{"id":"1603.08887","title":"Learning-Based Single-Document Summarization with Compression and Anaphoricity Constraints","created":"2016-03-29","cited_by_count":34},{"id":"1908.10328","title":"Movie Plot Analysis via Turning Point Identification","created":"2019-08-27","cited_by_count":34},{"id":"2109.02401","title":"Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization","created":"2021-09-06","cited_by_count":32},{"id":"2109.04609","title":"An Exploratory Study on Long Dialogue Summarization: What Works and What's Next","created":"2021-09-10","cited_by_count":28},{"id":"2012.07536","title":"Movie Summarization via Sparse Graph Construction","created":"2020-12-14","cited_by_count":22},{"id":"2111.08774","title":"Finding the Right Moment: Human-Assisted Trailer Creation via Task Composition","created":"2021-11-16","cited_by_count":12},{"id":"1707.08559","title":"Video Highlight Prediction Using Audience Chat Reactions","created":"2017-07-26","cited_by_count":11},{"id":"2106.05634","title":"Exploring Unsupervised Pretraining Objectives for Machine Translation","created":"2021-06-10","cited_by_count":3}],"next_cursor":null}