{"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/spatially-supervised-recurrent-convolutional","title":"Spatially Supervised Recurrent Convolutional Neural Networks for Visual Object Tracking","arxiv_id":"1607.05781","date":"2016-07-19","proceeding":null,"authors":["Guanghan Ning","Zhi Zhang","Chen Huang","Zhihai He","Xiaobo Ren","Haohong Wang"],"abstract":"In this paper, we develop a new approach of spatially supervised recurrent\nconvolutional neural networks for visual object tracking. Our recurrent\nconvolutional network exploits the history of locations as well as the\ndistinctive visual features learned by the deep neural networks. Inspired by\nrecent bounding box regression methods for object detection, we study the\nregression capability of Long Short-Term Memory (LSTM) in the temporal domain,\nand propose to concatenate high-level visual features produced by convolutional\nnetworks with region information. In contrast to existing deep learning based\ntrackers that use binary classification for region candidates, we use\nregression for direct prediction of the tracking locations both at the\nconvolutional layer and at the recurrent unit. Our extensive experimental\nresults and performance comparison with state-of-the-art tracking methods on\nchallenging benchmark video tracking datasets shows that our tracker is more\naccurate and robust while maintaining low computational cost. For most test\nvideo sequences, our method achieves the best tracking performance, often\noutperforms the second best by a large margin.","url_abs":"http://arxiv.org/abs/1607.05781v1","url_pdf":"http://arxiv.org/pdf/1607.05781v1.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":"spatially-supervised-recurrent-convolutional","repo_url":"https://github.com/Guanghan/ROLO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"spatially-supervised-recurrent-convolutional","repo_url":"https://github.com/zhangxiutao/ROLO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"visual-object-tracking","task_name":"Visual Object Tracking"},{"task_slug":"object-detection-1","task_name":"object-detection"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}