{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/an-empirical-study-of-language-cnn-for-image","title":"An Empirical Study of Language CNN for Image Captioning","arxiv_id":"1612.07086","date":"2016-12-21","proceeding":"ICCV 2017 10","authors":["Jiuxiang Gu","Gang Wang","Jianfei Cai","Tsuhan Chen"],"abstract":"Language Models based on recurrent neural networks have dominated recent\nimage caption generation tasks. In this paper, we introduce a Language CNN\nmodel which is suitable for statistical language modeling tasks and shows\ncompetitive performance in image captioning. In contrast to previous models\nwhich predict next word based on one previous word and hidden state, our\nlanguage CNN is fed with all the previous words and can model the long-range\ndependencies of history words, which are critical for image captioning. The\neffectiveness of our approach is validated on two datasets MS COCO and\nFlickr30K. Our extensive experimental results show that our method outperforms\nthe vanilla recurrent neural network based language models and is competitive\nwith the state-of-the-art methods.","url_abs":"http://arxiv.org/abs/1612.07086v3","url_pdf":"http://arxiv.org/pdf/1612.07086v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"an-empirical-study-of-language-cnn-for-image","repo_url":"https://github.com/gujiuxiang/language_cnn_iccv17","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":null},{"paper_slug":"an-empirical-study-of-language-cnn-for-image","repo_url":"https://github.com/showkeyjar/chinese_im2text.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"caption-generation","task_name":"Caption Generation"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1612.07086","atlas_url":"https://app.syntology.ai/?focus=1612.07086","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}