{"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/recurrent-soft-attention-model-for-common","title":"Recurrent Soft Attention Model for Common Object Recognition","arxiv_id":"1705.01921","date":"2017-05-04","proceeding":null,"authors":["Liliang Ren"],"abstract":"We propose the Recurrent Soft Attention Model, which integrates the visual\nattention from the original image to a LSTM memory cell through a down-sample\nnetwork. The model recurrently transmits visual attention to the memory cells\nfor glimpse mask generation, which is a more natural way for attention\nintegration and exploitation in general object detection and recognition\nproblem. We test our model under the metric of the top-1 accuracy on the\nCIFAR-10 dataset. The experiment shows that our down-sample network and\nfeedback mechanism plays an effective role among the whole network structure.","url_abs":"http://arxiv.org/abs/1705.01921v2","url_pdf":"http://arxiv.org/pdf/1705.01921v2.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":"recurrent-soft-attention-model-for-common","repo_url":"https://github.com/renll/RSAM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"model","task_name":"model"},{"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":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}