{"url":"/dataset/beat2","name":"BEAT2","full_name":"BEAT-SMPLX-FLAME","description_markdown":"We propose EMAGE, a framework to generate full-body human gestures from audio and masked gestures, encompassing facial, local body, hands, and global movements. To achieve this, we first introduce BEAT2 (BEAT-SMPLX-FLAME), a new mesh-level holistic co-speech dataset. BEAT2 combines MoShed SMPLX body with FLAME head parameters and further refines the modeling of head, neck, and finger movements, offering a community-standardized, high-quality 3D motion captured dataset.  EMAGE leverages masked body gesture priors during training to boost inference performance. It involves a Masked Audio Gesture Transformer, facilitating joint training on audio-to-gesture generation and masked gesture reconstruction to effectively encode audio and body gesture hints. Encoded body hints from masked gestures are then separately employed to generate facial and body movements.  Moreover, EMAGE adaptively merges speech features from the audio's rhythm and content and utilizes four compositional VQ-VAEs to enhance the results' fidelity and diversity. Experiments demonstrate that EMAGE generates holistic gestures with state-of-the-art performance and is flexible in accepting predefined spatial-temporal gesture inputs, generating complete, audio-synchronized results.","description_withheld":null,"homepage":"https://pantomatrix.github.io/EMAGE/","introduced_date":"2023-12-31","introduced_date_note":null,"introduced_by":{"paper":"/paper/emage-towards-unified-holistic-co-speech","title":"EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling","first_author":"Haiyang Liu","url":null},"license":{"name":"CC-BY-NC-4.0","url":"https://github.com/PantoMatrix/BEAT/blob/main/LICENSE.md"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"},{"name":"3d meshes","url":"/datasets/modality/3d-meshes"},{"name":"Time series","url":"/datasets/modality/time-series"}],"tasks":[{"name":"3D Face Animation","url":"/task/3d-face-animation","datasets_with_task":"/datasets/task/3d-face-animation"},{"name":"Gesture Generation","url":"/task/gesture-generation","datasets_with_task":"/datasets/task/gesture-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Spanish","url":"/datasets/language/spanish"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Japanese","url":"/datasets/language/japanese"}],"variants":["BEAT2"],"data_loaders":[],"num_papers_in_archive":23,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/gesture-generation-on-beat2","task":"Gesture Generation","dataset_variant":"BEAT2","rows":14,"metrics":["FGD"],"first_row_in_archive_order":{"model":"Intentional Gesture","paper":"/paper/intentional-gesture-deliver-your-intentions","metrics":{"FGD":"0.3790"},"code_links":[{"title":"andypinxinliu/Intentional-Gesture","url":"https://github.com/andypinxinliu/Intentional-Gesture"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/3d-face-animation-on-beat2","task":"3D Face Animation","dataset_variant":"BEAT2","rows":5,"metrics":["MSE"],"first_row_in_archive_order":{"model":"MambaTalk","paper":"/paper/mambatalk-efficient-holistic-gesture","metrics":{"MSE":"6.289"},"code_links":[{"title":"kkakkkka/MambaTalk","url":"https://github.com/kkakkkka/MambaTalk"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/intentional-gesture-deliver-your-intentions","title":"Intentional Gesture: Deliver Your Intentions with Gestures for Speech","date":"2025-05-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/echomask-speech-queried-attention-based-mask","title":"EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation","date":"2025-04-12","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/contextual-gesture-co-speech-gesture-video","title":"Contextual Gesture: Co-Speech Gesture Video Generation through Context-aware Gesture Representation","date":"2025-02-11","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/gesturelsm-latent-shortcut-based-co-speech","title":"GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling","date":"2025-01-31","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/semtalk-holistic-co-speech-motion-generation","title":"SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis","date":"2024-12-21","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/enabling-synergistic-full-body-control-in-1","title":"Enabling Synergistic Full-Body Control in Prompt-Based Co-Speech Motion Generation","date":"2024-10-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mambatalk-efficient-holistic-gesture","title":"MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models","date":"2024-03-14","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/emage-towards-unified-holistic-co-speech","title":"EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling","date":"2023-12-31","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/codetalker-speech-driven-3d-facial-animation","title":"CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior","date":"2023-01-06","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":2,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/generating-holistic-3d-human-motion-from","title":"Generating Holistic 3D Human Motion from Speech","date":"2022-12-08","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/learning-hierarchical-cross-modal-association","title":"Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation","date":"2022-03-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/beat-a-large-scale-semantic-and-emotional","title":"BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis","date":"2022-03-10","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/faceformer-speech-driven-3d-facial-animation","title":"FaceFormer: Speech-Driven 3D Facial Animation with Transformers","date":"2021-12-10","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-speech-driven-3d-conversational","title":"Learning Speech-driven 3D Conversational Gestures from Video","date":"2021-02-13","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/speech-gesture-generation-from-the-trimodal","title":"Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity","date":"2020-09-04","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/learning-individual-styles-of-conversational-1","title":"Learning Individual Styles of Conversational Gesture","date":"2019-06-10","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":5,"samples_harvested":25,"samples_ran":14,"samples_unverified":11,"pointer_only_for_licence":7,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}