Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agents
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2021
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909400167350272 |
|---|---|
| author | Bhattacharya, Uttaran Rewkowski, Nicholas Banerjee, Abhishek Guhan, Pooja Bera, Aniket Manocha, Dinesh |
| author_facet | Bhattacharya, Uttaran Rewkowski, Nicholas Banerjee, Abhishek Guhan, Pooja Bera, Aniket Manocha, Dinesh |
| contents | We present Text2Gestures, a transformer-based learning method to interactively generate emotive full-body gestures for virtual agents aligned with natural language text inputs. Our method generates emotionally expressive gestures by utilizing the relevant biomechanical features for body expressions, also known as affective features. We also consider the intended task corresponding to the text and the target virtual agents' intended gender and handedness in our generation pipeline. We train and evaluate our network on the MPI Emotional Body Expressions Database and observe that our network produces state-of-the-art performance in generating gestures for virtual agents aligned with the text for narration or conversation. Our network can generate these gestures at interactive rates on a commodity GPU. We conduct a web-based user study and observe that around 91% of participants indicated our generated gestures to be at least plausible on a five-point Likert Scale. The emotions perceived by the participants from the gestures are also strongly positively correlated with the corresponding intended emotions, with a minimum Pearson coefficient of 0.77 in the valence dimension. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2101_11101 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agents Bhattacharya, Uttaran Rewkowski, Nicholas Banerjee, Abhishek Guhan, Pooja Bera, Aniket Manocha, Dinesh Human-Computer Interaction Graphics We present Text2Gestures, a transformer-based learning method to interactively generate emotive full-body gestures for virtual agents aligned with natural language text inputs. Our method generates emotionally expressive gestures by utilizing the relevant biomechanical features for body expressions, also known as affective features. We also consider the intended task corresponding to the text and the target virtual agents' intended gender and handedness in our generation pipeline. We train and evaluate our network on the MPI Emotional Body Expressions Database and observe that our network produces state-of-the-art performance in generating gestures for virtual agents aligned with the text for narration or conversation. Our network can generate these gestures at interactive rates on a commodity GPU. We conduct a web-based user study and observe that around 91% of participants indicated our generated gestures to be at least plausible on a five-point Likert Scale. The emotions perceived by the participants from the gestures are also strongly positively correlated with the corresponding intended emotions, with a minimum Pearson coefficient of 0.77 in the valence dimension. |
| title | Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agents |
| topic | Human-Computer Interaction Graphics |
| url | https://arxiv.org/abs/2101.11101 |