{"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/kernel-cross-correlator","title":"Kernel Cross-Correlator","arxiv_id":"1709.05936","date":"2017-09-12","proceeding":null,"authors":["Chen Wang","Le Zhang","Lihua Xie","Junsong Yuan"],"abstract":"Cross-correlator plays a significant role in many visual perception tasks,\nsuch as object detection and tracking. Beyond the linear cross-correlator, this\npaper proposes a kernel cross-correlator (KCC) that breaks traditional\nlimitations. First, by introducing the kernel trick, the KCC extends the linear\ncross-correlation to non-linear space, which is more robust to signal noises\nand distortions. Second, the connection to the existing works shows that KCC\nprovides a unified solution for correlation filters. Third, KCC is applicable\nto any kernel function and is not limited to circulant structure on training\ndata, thus it is able to predict affine transformations with customized\nproperties. Last, by leveraging the fast Fourier transform (FFT), KCC\neliminates direct calculation of kernel vectors, thus achieves better\nperformance yet still with a reasonable computational cost. Comprehensive\nexperiments on visual tracking and human activity recognition using wearable\ndevices demonstrate its robustness, flexibility, and efficiency. The source\ncodes of both experiments are released at https://github.com/wang-chen/KCC","url_abs":"http://arxiv.org/abs/1709.05936v4","url_pdf":"http://arxiv.org/pdf/1709.05936v4.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":"kernel-cross-correlator","repo_url":"https://github.com/wang-chen/KCC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"kernel-cross-correlator","repo_url":"https://github.com/sair-lab/ni-slam","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"kernel-cross-correlator","repo_url":"https://github.com/wang-chen/correlation_flow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"activity-recognition","task_name":"Activity Recognition"},{"task_slug":"human-activity-recognition","task_name":"Human Activity Recognition"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"visual-tracking","task_name":"Visual Tracking"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.05936","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}