{"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/real-time-mdnet","title":"Real-Time MDNet","arxiv_id":"1808.08834","date":"2018-08-27","proceeding":"ECCV 2018 9","authors":["Ilchae Jung","Jeany Son","Mooyeol Baek","Bohyung Han"],"abstract":"We present a fast and accurate visual tracking algorithm based on the\nmulti-domain convolutional neural network (MDNet). The proposed approach\naccelerates feature extraction procedure and learns more discriminative models\nfor instance classification; it enhances representation quality of target and\nbackground by maintaining a high resolution feature map with a large receptive\nfield per activation. We also introduce a novel loss term to differentiate\nforeground instances across multiple domains and learn a more discriminative\nembedding of target objects with similar semantics. The proposed techniques are\nintegrated into the pipeline of a well known CNN-based visual tracking\nalgorithm, MDNet. We accomplish approximately 25 times speed-up with almost\nidentical accuracy compared to MDNet. Our algorithm is evaluated in multiple\npopular tracking benchmark datasets including OTB2015, UAV123, and TempleColor,\nand outperforms the state-of-the-art real-time tracking methods consistently\neven without dataset-specific parameter tuning.","url_abs":"http://arxiv.org/abs/1808.08834v1","url_pdf":"http://arxiv.org/pdf/1808.08834v1.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":"real-time-mdnet","repo_url":"https://github.com/Amgao/RLS-RTMDNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"real-time-mdnet","repo_url":"https://github.com/BossBobxuan/RT-MDNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"real-time-mdnet","repo_url":"https://github.com/IlchaeJung/RT-MDNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"visual-tracking","task_name":"Visual Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.08834","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}