{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"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":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"2303.15056","title":"ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks","created":"2023-03-27","cited_by_count":870},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"id":"1802.01886","title":"Texygen: A Benchmarking Platform for Text Generation Models","created":"2018-02-06","cited_by_count":491},{"id":"2111.02358","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","created":"2021-11-03","cited_by_count":425},{"id":"1604.01696","title":"A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories","created":"2016-04-06","cited_by_count":417},{"id":"2307.02486","title":"LongNet: Scaling Transformers to 1,000,000,000 Tokens","created":"2023-07-05","cited_by_count":204},{"id":"2210.06774","title":"Re3: Generating Longer Stories With Recursive Reprompting and Revision","created":"2022-10-13","cited_by_count":193},{"id":"1605.03705","title":"Movie Description","created":"2016-05-12","cited_by_count":181},{"id":"1604.03968","title":"Visual Storytelling","created":"2016-04-13","cited_by_count":176},{"id":"2111.13196","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","created":"2021-11-25","cited_by_count":162},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118},{"id":"1502.08029","title":"Describing Videos by Exploiting Temporal Structure","created":"2015-02-27","cited_by_count":88},{"id":"1905.07841","title":"Multimodal Transformer with Multi-View Visual Representation for Image Captioning","created":"2019-05-20","cited_by_count":86},{"id":"1707.00836","title":"DeepStory: Video Story QA by Deep Embedded Memory Networks","created":"2017-07-04","cited_by_count":68},{"id":"2010.01717","title":"STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation","created":"2020-10-04","cited_by_count":56},{"id":"1804.09160","title":"No Metrics Are Perfect: Adversarial Reward Learning for Visual Storytelling","created":"2018-04-24","cited_by_count":46},{"id":"1909.03480","title":"Story Realization: Expanding Plot Events into Sentences","created":"2019-09-08","cited_by_count":35},{"id":"1704.03162","title":"Show, Ask, Attend, and Answer: A Strong Baseline For Visual Question Answering","created":"2017-04-11","cited_by_count":31},{"id":"1812.05634","title":"Adversarial Inference for Multi-Sentence Video Description","created":"2018-12-13","cited_by_count":31},{"id":"2301.08571","title":"Visual Writing Prompts: Character-Grounded Story Generation with Curated Image Sequences","created":"2023-01-20","cited_by_count":31},{"id":"1707.05501","title":"Story Generation from Sequence of Independent Short Descriptions","created":"2017-07-18","cited_by_count":26},{"id":"1912.01496","title":"Knowledge-Enriched Visual Storytelling","created":"2019-12-03","cited_by_count":26},{"id":"1805.10973","title":"GLAC Net: GLocal Attention Cascading Networks for Multi-image Cued Story Generation","created":"2018-05-28","cited_by_count":23},{"id":"1805.08191","title":"Hierarchically Structured Reinforcement Learning for Topically Coherent Visual Story Generation","created":"2018-05-21","cited_by_count":21},{"id":"2105.06950","title":"Plot and Rework: Modeling Storylines for Visual Storytelling","created":"2021-05-14","cited_by_count":14},{"id":"1806.00738","title":"Contextualize, Show and Tell: A Neural Visual Storyteller","created":"2018-06-03","cited_by_count":13},{"id":"2002.00774","title":"Hide-and-Tell: Learning to Bridge Photo Streams for Visual Storytelling","created":"2020-02-03","cited_by_count":13},{"id":"1708.02977","title":"Hierarchically-Attentive RNN for Album Summarization and Storytelling","created":"2017-08-09","cited_by_count":10},{"id":"1906.01764","title":"Visual Story Post-Editing","created":"2019-06-05","cited_by_count":10},{"id":"1807.08077","title":"A Pipeline for Creative Visual Storytelling","created":"2018-07-21","cited_by_count":7},{"id":"2310.04529","title":"Envisioning Narrative Intelligence: A Creative Visual Storytelling Anthology","created":"2023-10-06","cited_by_count":7},{"id":"1507.06120","title":"Towards Storytelling from Visual Lifelogging: An Overview","created":"2015-07-22","cited_by_count":6},{"id":"1904.03366","title":"The Steep Road to Happily Ever After: An Analysis of Current Visual Storytelling Models","created":"2019-04-06","cited_by_count":6},{"id":"2310.15129","title":"Location-Aware Visual Question Generation with Lightweight Models","created":"2023-10-23","cited_by_count":4},{"id":"1903.02230","title":"Dixit: Interactive Visual Storytelling via Term Manipulation","created":"2019-03-06","cited_by_count":2},{"id":"2103.05103","title":"Image Captioning using Multiple Transformers for Self-Attention Mechanism","created":"2021-02-14","cited_by_count":2}],"next_cursor":null}