{"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/cnncnn-convolutional-decoders-for-image","title":"CNN+CNN: Convolutional Decoders for Image Captioning","arxiv_id":"1805.09019","date":"2018-05-23","proceeding":null,"authors":["Qingzhong Wang","Antoni B. Chan"],"abstract":"Image captioning is a challenging task that combines the field of computer\nvision and natural language processing. A variety of approaches have been\nproposed to achieve the goal of automatically describing an image, and\nrecurrent neural network (RNN) or long-short term memory (LSTM) based models\ndominate this field. However, RNNs or LSTMs cannot be calculated in parallel\nand ignore the underlying hierarchical structure of a sentence. In this paper,\nwe propose a framework that only employs convolutional neural networks (CNNs)\nto generate captions. Owing to parallel computing, our basic model is around 3\ntimes faster than NIC (an LSTM-based model) during training time, while also\nproviding better results. We conduct extensive experiments on MSCOCO and\ninvestigate the influence of the model width and depth. Compared with\nLSTM-based models that apply similar attention mechanisms, our proposed models\nachieves comparable scores of BLEU-1,2,3,4 and METEOR, and higher scores of\nCIDEr. We also test our model on the paragraph annotation dataset, and get\nhigher CIDEr score compared with hierarchical LSTMs","url_abs":"http://arxiv.org/abs/1805.09019v1","url_pdf":"http://arxiv.org/pdf/1805.09019v1.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":"cnncnn-convolutional-decoders-for-image","repo_url":"https://github.com/qingzwang/GHA-ImageCaptioning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.09019","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}