{"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-filter-learning-for-visual-tracking","title":"Recurrent Filter Learning for Visual Tracking","arxiv_id":"1708.03874","date":"2017-08-13","proceeding":null,"authors":["Tianyu Yang","Antoni B. Chan"],"abstract":"Recently using convolutional neural networks (CNNs) has gained popularity in\nvisual tracking, due to its robust feature representation of images. Recent\nmethods perform online tracking by fine-tuning a pre-trained CNN model to the\nspecific target object using stochastic gradient descent (SGD)\nback-propagation, which is usually time-consuming. In this paper, we propose a\nrecurrent filter generation methods for visual tracking. We directly feed the\ntarget's image patch to a recurrent neural network (RNN) to estimate an\nobject-specific filter for tracking. As the video sequence is a spatiotemporal\ndata, we extend the matrix multiplications of the fully-connected layers of the\nRNN to a convolution operation on feature maps, which preserves the target's\nspatial structure and also is memory-efficient. The tracked object in the\nsubsequent frames will be fed into the RNN to adapt the generated filters to\nappearance variations of the target. Note that once the off-line training\nprocess of our network is finished, there is no need to fine-tune the network\nfor specific objects, which makes our approach more efficient than methods that\nuse iterative fine-tuning to online learn the target. Extensive experiments\nconducted on widely used benchmarks, OTB and VOT, demonstrate encouraging\nresults compared to other recent methods.","url_abs":"http://arxiv.org/abs/1708.03874v1","url_pdf":"http://arxiv.org/pdf/1708.03874v1.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-filter-learning-for-visual-tracking","repo_url":"https://github.com/skyoung/RFL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"visual-tracking","task_name":"Visual Tracking"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}