{"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/skeleton-based-action-recognition-using-1","title":"Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep cnn","arxiv_id":"1704.05645","date":"2017-04-19","proceeding":null,"authors":["Bo Li","Mingyi He","Xuelian Cheng","Yu-cheng Chen","Yuchao Dai"],"abstract":"This paper presents an image classification based approach for skeleton-based\nvideo action recognition problem. Firstly, A dataset independent\ntranslation-scale invariant image mapping method is proposed, which transformes\nthe skeleton videos to colour images, named skeleton-images. Secondly, A\nmulti-scale deep convolutional neural network (CNN) architecture is proposed\nwhich could be built and fine-tuned on the powerful pre-trained CNNs, e.g.,\nAlexNet, VGGNet, ResNet etal.. Even though the skeleton-images are very\ndifferent from natural images, the fine-tune strategy still works well. At\nlast, we prove that our method could also work well on 2D skeleton video data.\nWe achieve the state-of-the-art results on the popular benchmard datasets e.g.\nNTU RGB+D, UTD-MHAD, MSRC-12, and G3D. Especially on the largest and challenge\nNTU RGB+D, UTD-MHAD, and MSRC-12 dataset, our method outperforms other methods\nby a large margion, which proves the efficacy of the proposed method.","url_abs":"http://arxiv.org/abs/1704.05645v2","url_pdf":"http://arxiv.org/pdf/1704.05645v2.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":[],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"skeleton-based-action-recognition","task_name":"Skeleton Based Action Recognition"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D","model":"3scale ResNet152","rank_in_archive_order":96,"of":135,"metrics":{"Accuracy (CS)":"85.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.05645","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}