{"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/attt2m-text-driven-human-motion-generation-1","title":"AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism","arxiv_id":"2309.00796","date":"2023-09-02","proceeding":"ICCV 2023 1","authors":["Chongyang Zhong","Lei Hu","Zihao Zhang","Shihong Xia"],"abstract":"Generating 3D human motion based on textual descriptions has been a research focus in recent years. It requires the generated motion to be diverse, natural, and conform to the textual description. Due to the complex spatio-temporal nature of human motion and the difficulty in learning the cross-modal relationship between text and motion, text-driven motion generation is still a challenging problem. To address these issues, we propose \\textbf{AttT2M}, a two-stage method with multi-perspective attention mechanism: \\textbf{body-part attention} and \\textbf{global-local motion-text attention}. The former focuses on the motion embedding perspective, which means introducing a body-part spatio-temporal encoder into VQ-VAE to learn a more expressive discrete latent space. The latter is from the cross-modal perspective, which is used to learn the sentence-level and word-level motion-text cross-modal relationship. The text-driven motion is finally generated with a generative transformer. Extensive experiments conducted on HumanML3D and KIT-ML demonstrate that our method outperforms the current state-of-the-art works in terms of qualitative and quantitative evaluation, and achieve fine-grained synthesis and action2motion. Our code is in https://github.com/ZcyMonkey/AttT2M","url_abs":"https://arxiv.org/abs/2309.00796v1","url_pdf":"https://arxiv.org/pdf/2309.00796v1.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":"attt2m-text-driven-human-motion-generation-1","repo_url":"https://github.com/zcymonkey/attt2m","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"motion-generation","task_name":"Motion Generation"},{"task_slug":"motion-synthesis","task_name":"Motion Synthesis"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"focus","method_name":"Focus"},{"method_slug":"vq-vae","method_name":"VQ-VAE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/motion-synthesis-on-humanml3d","task":"Motion Synthesis","dataset":"HumanML3D","model":"AttT2M","rank_in_archive_order":18,"of":37,"metrics":{"Diversity":"9.700","FID":"0.112","Multimodality":"2.452","R Precision Top3":"0.786 "},"uses_additional_data":false},{"leaderboard":"/sota/motion-synthesis-on-kit-motion-language","task":"Motion Synthesis","dataset":"KIT Motion-Language","model":"AttT2M","rank_in_archive_order":25,"of":31,"metrics":{"Diversity":"10.96","FID":"0.870","Multimodality":"2.281","R Precision Top3":"0.751"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.00796","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.00796"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zcymonkey/attt2m","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/ZcyMonkey/AttT2M","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_honours":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"b5884fc2a88a2dca","entry":"PE1d_sincos","repo":"ZcyMonkey/AttT2M","repo_kind":"official","path":"models/pos_encoding.py","file_url":"https://github.com/ZcyMonkey/AttT2M/blob/HEAD/models/pos_encoding.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b5884fc2a88a2dca"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}