{"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/image-captioning-with-deep-bidirectional","title":"Image Captioning with Deep Bidirectional LSTMs","arxiv_id":"1604.00790","date":"2016-04-04","proceeding":null,"authors":["Cheng Wang","Haojin Yang","Christian Bartz","Christoph Meinel"],"abstract":"This work presents an end-to-end trainable deep bidirectional LSTM\n(Long-Short Term Memory) model for image captioning. Our model builds on a deep\nconvolutional neural network (CNN) and two separate LSTM networks. It is\ncapable of learning long term visual-language interactions by making use of\nhistory and future context information at high level semantic space. Two novel\ndeep bidirectional variant models, in which we increase the depth of\nnonlinearity transition in different way, are proposed to learn hierarchical\nvisual-language embeddings. Data augmentation techniques such as multi-crop,\nmulti-scale and vertical mirror are proposed to prevent overfitting in training\ndeep models. We visualize the evolution of bidirectional LSTM internal states\nover time and qualitatively analyze how our models \"translate\" image to\nsentence. Our proposed models are evaluated on caption generation and\nimage-sentence retrieval tasks with three benchmark datasets: Flickr8K,\nFlickr30K and MSCOCO datasets. We demonstrate that bidirectional LSTM models\nachieve highly competitive performance to the state-of-the-art results on\ncaption generation even without integrating additional mechanism (e.g. object\ndetection, attention model etc.) and significantly outperform recent methods on\nretrieval task.","url_abs":"http://arxiv.org/abs/1604.00790v3","url_pdf":"http://arxiv.org/pdf/1604.00790v3.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":"image-captioning-with-deep-bidirectional","repo_url":"https://github.com/deepsemantic/image_captioning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"caption-generation","task_name":"Caption Generation"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-retrieval","task_name":"Sentence Retrieval"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1604.00790","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}