{"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/densebox-unifying-landmark-localization-with","title":"DenseBox: Unifying Landmark Localization with End to End Object Detection","arxiv_id":"1509.04874","date":"2015-09-16","proceeding":null,"authors":["Lichao Huang","Yi Yang","Yafeng Deng","Yinan Yu"],"abstract":"How can a single fully convolutional neural network (FCN) perform on object\ndetection? We introduce DenseBox, a unified end-to-end FCN framework that\ndirectly predicts bounding boxes and object class confidences through all\nlocations and scales of an image. Our contribution is two-fold. First, we show\nthat a single FCN, if designed and optimized carefully, can detect multiple\ndifferent objects extremely accurately and efficiently. Second, we show that\nwhen incorporating with landmark localization during multi-task learning,\nDenseBox further improves object detection accuray. We present experimental\nresults on public benchmark datasets including MALF face detection and KITTI\ncar detection, that indicate our DenseBox is the state-of-the-art system for\ndetecting challenging objects such as faces and cars.","url_abs":"http://arxiv.org/abs/1509.04874v3","url_pdf":"http://arxiv.org/pdf/1509.04874v3.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":"densebox-unifying-landmark-localization-with","repo_url":"https://github.com/jimheaton/Ultra96_ML_Embedded_Workshop","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"densebox-unifying-landmark-localization-with","repo_url":"https://github.com/yangyi02/densebox","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"face-detection","task_name":"Face Detection"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1509.04874","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}