{"url":"/sota/gesture-generation-on-beat2","task":{"name":"Gesture Generation","url":"/task/gesture-generation","note":null},"dataset":{"name":"BEAT2","url":"/dataset/beat2"},"category":"Robots","categories":["Robots"],"category_note":null,"description":"Generation of gestures, as a sequence of 3d poses","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["FGD"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"FGD":null}},"counts":{"rows":14,"rows_with_code":10,"rows_with_paper_page":14,"rows_dated":14,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Intentional Gesture","metrics":{"FGD":"0.3790"},"uses_additional_data":false,"paper_date":"2025-05-21","paper":"/paper/intentional-gesture-deliver-your-intentions","paper_url":"https://arxiv.org/abs/2505.15197v1","paper_title":"Intentional Gesture: Deliver Your Intentions with Gestures for Speech","code":"https://github.com/andypinxinliu/Intentional-Gesture","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"GestureLSM","metrics":{"FGD":"0.4040"},"uses_additional_data":false,"paper_date":"2025-01-31","paper":"/paper/gesturelsm-latent-shortcut-based-co-speech","paper_url":"https://arxiv.org/abs/2501.18898v2","paper_title":"GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling","code":"https://github.com/andypinxinliu/GestureLSM","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"SemTalk","metrics":{"FGD":"0.4278"},"uses_additional_data":false,"paper_date":"2024-12-21","paper":"/paper/semtalk-holistic-co-speech-motion-generation","paper_url":"https://arxiv.org/abs/2412.16563v2","paper_title":"SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"Contexual Gesture","metrics":{"FGD":"0.4434"},"uses_additional_data":false,"paper_date":"2025-02-11","paper":"/paper/contextual-gesture-co-speech-gesture-video","paper_url":"https://arxiv.org/abs/2502.07239v1","paper_title":"Contextual Gesture: Co-Speech Gesture Video Generation through Context-aware Gesture Representation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"EchoMask","metrics":{"FGD":"0.4623"},"uses_additional_data":false,"paper_date":"2025-04-12","paper":"/paper/echomask-speech-queried-attention-based-mask","paper_url":"https://arxiv.org/abs/2504.09209v2","paper_title":"EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"Syntalker","metrics":{"FGD":"0.4687"},"uses_additional_data":false,"paper_date":"2024-10-01","paper":"/paper/enabling-synergistic-full-body-control-in-1","paper_url":"https://arxiv.org/abs/2410.00464v1","paper_title":"Enabling Synergistic Full-Body Control in Prompt-Based Co-Speech Motion Generation","code":"https://github.com/RobinWitch/SynTalker","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"MambaTalk","metrics":{"FGD":"0.5366"},"uses_additional_data":false,"paper_date":"2024-03-14","paper":"/paper/mambatalk-efficient-holistic-gesture","paper_url":"https://arxiv.org/abs/2403.09471v6","paper_title":"MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models","code":"https://github.com/kkakkkka/MambaTalk","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"EMAGE","metrics":{"FGD":"0.5512"},"uses_additional_data":false,"paper_date":"2023-12-31","paper":"/paper/emage-towards-unified-holistic-co-speech","paper_url":"https://arxiv.org/abs/2401.00374v5","paper_title":"EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling","code":"https://github.com/PantoMatrix/PantoMatrix","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":9,"model":"TalkShow","metrics":{"FGD":"0.6209"},"uses_additional_data":false,"paper_date":"2022-12-08","paper":"/paper/generating-holistic-3d-human-motion-from","paper_url":"https://arxiv.org/abs/2212.04420v2","paper_title":"Generating Holistic 3D Human Motion from Speech","code":"https://github.com/yhw-yhw/talkshow","n_code_links":3,"syntology":null},{"rank_in_archive_order":10,"model":"CaMN","metrics":{"FGD":"0.6644"},"uses_additional_data":false,"paper_date":"2022-03-10","paper":"/paper/beat-a-large-scale-semantic-and-emotional","paper_url":"https://arxiv.org/abs/2203.05297v5","paper_title":"BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis","code":"https://github.com/PantoMatrix/PantoMatrix","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":11,"model":"Habibie","metrics":{"FGD":"0.9040"},"uses_additional_data":false,"paper_date":"2021-02-13","paper":"/paper/learning-speech-driven-3d-conversational","paper_url":"https://arxiv.org/abs/2102.06837v1","paper_title":"Learning Speech-driven 3D Conversational Gestures from Video","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"HA2G","metrics":{"FGD":"1.232"},"uses_additional_data":false,"paper_date":"2022-03-24","paper":"/paper/learning-hierarchical-cross-modal-association","paper_url":"https://arxiv.org/abs/2203.13161v1","paper_title":"Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation","code":"https://github.com/alvinliu0/HA2G","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"Trimodal","metrics":{"FGD":"1.241"},"uses_additional_data":false,"paper_date":"2020-09-04","paper":"/paper/speech-gesture-generation-from-the-trimodal","paper_url":"https://arxiv.org/abs/2009.02119v1","paper_title":"Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity","code":"https://github.com/ai4r/Gesture-Generation-from-Trimodal-Context","n_code_links":2,"syntology":null},{"rank_in_archive_order":14,"model":"S2G","metrics":{"FGD":"2.815"},"uses_additional_data":false,"paper_date":"2019-06-10","paper":"/paper/learning-individual-styles-of-conversational-1","paper_url":"https://arxiv.org/abs/1906.04160v1","paper_title":"Learning Individual Styles of Conversational Gesture","code":"https://github.com/amirbar/speech2gesture","n_code_links":2,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":3,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":8,"n_unverified":0,"n_samples":8,"n_pointer_only_licence":7,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":8,"n_unverified":0,"n_samples":8,"n_pointer_only_licence":7,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}