{"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/a-bag-of-words-equivalent-recurrent-neural","title":"A Bag-of-Words Equivalent Recurrent Neural Network for Action Recognition","arxiv_id":"1703.08089","date":"2017-03-23","proceeding":null,"authors":["Alexander Richard","Juergen Gall"],"abstract":"The traditional bag-of-words approach has found a wide range of applications\nin computer vision. The standard pipeline consists of a generation of a visual\nvocabulary, a quantization of the features into histograms of visual words, and\na classification step for which usually a support vector machine in combination\nwith a non-linear kernel is used. Given large amounts of data, however, the\nmodel suffers from a lack of discriminative power. This applies particularly\nfor action recognition, where the vast amount of video features needs to be\nsubsampled for unsupervised visual vocabulary generation. Moreover, the kernel\ncomputation can be very expensive on large datasets. In this work, we propose a\nrecurrent neural network that is equivalent to the traditional bag-of-words\napproach but enables for the application of discriminative training. The model\nfurther allows to incorporate the kernel computation into the neural network\ndirectly, solving the complexity issue and allowing to represent the complete\nclassification system within a single network. We evaluate our method on four\nrecent action recognition benchmarks and show that the conventional model as\nwell as sparse coding methods are outperformed.","url_abs":"http://arxiv.org/abs/1703.08089v1","url_pdf":"http://arxiv.org/pdf/1703.08089v1.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":"a-bag-of-words-equivalent-recurrent-neural","repo_url":"https://github.com/alexanderrichard/squirrel","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}