{"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/senticap-generating-image-descriptions-with","title":"SentiCap: Generating Image Descriptions with Sentiments","arxiv_id":"1510.01431","date":"2015-10-06","proceeding":null,"authors":["Alexander Mathews","Lexing Xie","Xuming He"],"abstract":"The recent progress on image recognition and language modeling is making\nautomatic description of image content a reality. However, stylized,\nnon-factual aspects of the written description are missing from the current\nsystems. One such style is descriptions with emotions, which is commonplace in\neveryday communication, and influences decision-making and interpersonal\nrelationships. We design a system to describe an image with emotions, and\npresent a model that automatically generates captions with positive or negative\nsentiments. We propose a novel switching recurrent neural network with\nword-level regularization, which is able to produce emotional image captions\nusing only 2000+ training sentences containing sentiments. We evaluate the\ncaptions with different automatic and crowd-sourcing metrics. Our model\ncompares favourably in common quality metrics for image captioning. In 84.6% of\ncases the generated positive captions were judged as being at least as\ndescriptive as the factual captions. Of these positive captions 88% were\nconfirmed by the crowd-sourced workers as having the appropriate sentiment.","url_abs":"http://arxiv.org/abs/1510.01431v2","url_pdf":"http://arxiv.org/pdf/1510.01431v2.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":[],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"descriptive","task_name":"Descriptive"},{"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":[{"slug":"senticap","name":"SentiCap","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1510.01431","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}