{"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/tmr-text-to-motion-retrieval-using","title":"TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis","arxiv_id":"2305.00976","date":"2023-05-02","proceeding":"ICCV 2023 1","authors":["Mathis Petrovich","Michael J. Black","Gül Varol"],"abstract":"In this paper, we present TMR, a simple yet effective approach for text to 3D human motion retrieval. While previous work has only treated retrieval as a proxy evaluation metric, we tackle it as a standalone task. Our method extends the state-of-the-art text-to-motion synthesis model TEMOS, and incorporates a contrastive loss to better structure the cross-modal latent space. We show that maintaining the motion generation loss, along with the contrastive training, is crucial to obtain good performance. We introduce a benchmark for evaluation and provide an in-depth analysis by reporting results on several protocols. Our extensive experiments on the KIT-ML and HumanML3D datasets show that TMR outperforms the prior work by a significant margin, for example reducing the median rank from 54 to 19. Finally, we showcase the potential of our approach on moment retrieval. Our code and models are publicly available at https://mathis.petrovich.fr/tmr.","url_abs":"https://arxiv.org/abs/2305.00976v2","url_pdf":"https://arxiv.org/pdf/2305.00976v2.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":"tmr-text-to-motion-retrieval-using","repo_url":"https://github.com/Mathux/TMR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"moment-retrieval","task_name":"Moment Retrieval"},{"task_slug":"motion-generation","task_name":"Motion Generation"},{"task_slug":"motion-synthesis","task_name":"Motion Synthesis"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-to-3d","task_name":"Text to 3D"},{"task_slug":"text-to-3d-human","task_name":"text-to-3d-human"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.00976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.00976"}},"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/Mathux/TMR","reach":null}],"summary":{"ran":5,"ran_draft_wrong":3,"ran_fixture":1,"unverified":3},"by_repo_kind":{"listed":{"samples":12,"ran":9,"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":"741be0f1e89597a0","entry":"InfoNCE_with_filtering","repo":"Mathux/TMR","repo_kind":"listed","path":"src/model/tmr.py","file_url":"https://github.com/Mathux/TMR/blob/HEAD/src/model/tmr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"741be0f1e89597a0"}},{"code_sha256_prefix":"7742734b4ba50302","entry":"KLLoss","repo":"Mathux/TMR","repo_kind":"listed","path":"src/model/tmr.py","file_url":"https://github.com/Mathux/TMR/blob/HEAD/src/model/tmr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7742734b4ba50302"}},{"code_sha256_prefix":"6c77bd6ecc1b5f00","entry":"all_contrastive_metrics","repo":"Mathux/TMR","repo_kind":"listed","path":"src/model/tmr.py","file_url":"https://github.com/Mathux/TMR/blob/HEAD/src/model/tmr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6c77bd6ecc1b5f00"}},{"code_sha256_prefix":"2eaeeecbcc2bce92","entry":"break_ties_average","repo":"Mathux/TMR","repo_kind":"listed","path":"src/model/tmr.py","file_url":"https://github.com/Mathux/TMR/blob/HEAD/src/model/tmr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2eaeeecbcc2bce92"}},{"code_sha256_prefix":"8837faea84531612","entry":"break_ties_optimistically","repo":"Mathux/TMR","repo_kind":"listed","path":"src/model/tmr.py","file_url":"https://github.com/Mathux/TMR/blob/HEAD/src/model/tmr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8837faea84531612"}},{"code_sha256_prefix":"a666387ccfdf74bd","entry":"cols2metrics","repo":"Mathux/TMR","repo_kind":"listed","path":"src/model/tmr.py","file_url":"https://github.com/Mathux/TMR/blob/HEAD/src/model/tmr.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a666387ccfdf74bd"}},{"code_sha256_prefix":"8f87ba84f2a8ebd7","entry":"get_sim_matrix","repo":"Mathux/TMR","repo_kind":"listed","path":"src/model/tmr.py","file_url":"https://github.com/Mathux/TMR/blob/HEAD/src/model/tmr.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8f87ba84f2a8ebd7"}},{"code_sha256_prefix":"e852f499f639146d","entry":"length_to_mask","repo":"Mathux/TMR","repo_kind":"listed","path":"src/model/tmr.py","file_url":"https://github.com/Mathux/TMR/blob/HEAD/src/model/tmr.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e852f499f639146d"}},{"code_sha256_prefix":"129462f7f783e0f3","entry":"transpose","repo":"Mathux/TMR","repo_kind":"listed","path":"src/model/tmr.py","file_url":"https://github.com/Mathux/TMR/blob/HEAD/src/model/tmr.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"129462f7f783e0f3"}},{"code_sha256_prefix":"d0dce6a339845713","entry":"TEMOS","repo":"Mathux/TMR","repo_kind":"listed","path":"src/model/tmr.py","file_url":"https://github.com/Mathux/TMR/blob/HEAD/src/model/tmr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d0dce6a339845713"}},{"code_sha256_prefix":"70c2a5a5837894e3","entry":"TMR","repo":"Mathux/TMR","repo_kind":"listed","path":"src/model/tmr.py","file_url":"https://github.com/Mathux/TMR/blob/HEAD/src/model/tmr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"70c2a5a5837894e3"}},{"code_sha256_prefix":"844c670c33598db4","entry":"contrastive_metrics","repo":"Mathux/TMR","repo_kind":"listed","path":"src/model/tmr.py","file_url":"https://github.com/Mathux/TMR/blob/HEAD/src/model/tmr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"844c670c33598db4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}