{"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/harrison-a-benchmark-on-hashtag","title":"HARRISON: A Benchmark on HAshtag Recommendation for Real-world Images in Social Networks","arxiv_id":"1605.05054","date":"2016-05-17","proceeding":null,"authors":["Minseok Park","Hanxiang Li","Junmo Kim"],"abstract":"Simple, short, and compact hashtags cover a wide range of information on\nsocial networks. Although many works in the field of natural language\nprocessing (NLP) have demonstrated the importance of hashtag recommendation,\nhashtag recommendation for images has barely been studied. In this paper, we\nintroduce the HARRISON dataset, a benchmark on hashtag recommendation for real\nworld images in social networks. The HARRISON dataset is a realistic dataset,\ncomposed of 57,383 photos from Instagram and an average of 4.5 associated\nhashtags for each photo. To evaluate our dataset, we design a baseline\nframework consisting of visual feature extractor based on convolutional neural\nnetwork (CNN) and multi-label classifier based on neural network. Based on this\nframework, two single feature-based models, object-based and scene-based model,\nand an integrated model of them are evaluated on the HARRISON dataset. Our\ndataset shows that hashtag recommendation task requires a wide and contextual\nunderstanding of the situation conveyed in the image. As far as we know, this\nwork is the first vision-only attempt at hashtag recommendation for real world\nimages in social networks. We expect this benchmark to accelerate the\nadvancement of hashtag recommendation.","url_abs":"http://arxiv.org/abs/1605.05054v1","url_pdf":"http://arxiv.org/pdf/1605.05054v1.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":"harrison-a-benchmark-on-hashtag","repo_url":"https://github.com/minstone/HARRISON-Dataset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"harrison","name":"HARRISON","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1605.05054","atlas_url":"https://app.syntology.ai/?focus=1605.05054","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}