{"url":"/method/dynamic-keypoint-head","slug":"dynamic-keypoint-head","name":"Dynamic Keypoint Head","full_name":"Dynamic Keypoint Head","full_name_withheld":false,"description_markdown":"**Dynamic Keypoint Head** is an output head for pose estimation that are conditioned on each instance (person), and can encode the instance concept in the dynamically-generated weights of their filters. They are used in the [FCPose](https://paperswithcode.com/method/fcpose) architecture.\r\n\r\nThe Figure shows the core idea. $F$ denotes a level of feature maps. \"Rel. Coord.\" means the relative coordinates, denoting the relative offsets from the locations of $F$ to the location where the filters are generated. Refer to the text for details. $f\\_{\\theta\\_{i}}$ is the dynamically-generated keypoint head for the $i$-th person instance. Note that each person instance has its own keypoint head.","description_state":"present","introduced_year":null,"introduced_by":{"title":"FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions","paper":"/paper/fcpose-fully-convolutional-multi-person-pose","first_author":"Weian Mao","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/fcpose-fully-convolutional-multi-person-pose"},"source":{"url":"https://arxiv.org/abs/2105.14185v1","title":"FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Output Heads","url":"/methods/category/output-heads","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/fcpose-fully-convolutional-multi-person-pose","title":"FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions","date":"2021-05-29","arxiv_id":"2105.14185","n_code_links":3,"syntology":null}],"papers_shown":1,"tasks":[{"task":"/task/keypoint-estimation","name":"Keypoint Estimation","papers":1},{"task":"/task/multi-person-pose-estimation","name":"Multi-Person Pose Estimation","papers":1},{"task":"/task/pose-estimation","name":"Pose Estimation","papers":1}],"tasks_shown":3,"n_tasks":3,"usage_by_year":[{"year":"2021","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/dynamic-keypoint-head"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}