AROS: Affordance Recognition with One-Shot Human Stances
We present Affordance Recognition with One-Shot Human Stances (AROS), a one-shot learning approach that uses an explicit representation of interactions between highly articulated human poses and 3D scenes. The approach is one-shot since it does not require iterative training or retraining to add new...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-05-01
|
| Series: | Frontiers in Robotics and AI |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frobt.2023.1076780/full |
| _version_ | 1797835608769429504 |
|---|---|
| author | Abel Pacheco-Ortega Walterio Mayol-Cuevas Walterio Mayol-Cuevas |
| author_facet | Abel Pacheco-Ortega Walterio Mayol-Cuevas Walterio Mayol-Cuevas |
| author_sort | Abel Pacheco-Ortega |
| collection | DOAJ |
| description | We present Affordance Recognition with One-Shot Human Stances (AROS), a one-shot learning approach that uses an explicit representation of interactions between highly articulated human poses and 3D scenes. The approach is one-shot since it does not require iterative training or retraining to add new affordance instances. Furthermore, only one or a small handful of examples of the target pose are needed to describe the interactions. Given a 3D mesh of a previously unseen scene, we can predict affordance locations that support the interactions and generate corresponding articulated 3D human bodies around them. We evaluate the performance of our approach on three public datasets of scanned real environments with varied degrees of noise. Through rigorous statistical analysis of crowdsourced evaluations, our results show that our one-shot approach is preferred up to 80% of the time over data-intensive baselines. |
| first_indexed | 2024-04-09T14:56:19Z |
| format | Article |
| id | doaj.art-5ded23a3c05a4ded927bc2146b4cef77 |
| institution | Directory Open Access Journal |
| issn | 2296-9144 |
| language | English |
| last_indexed | 2024-04-09T14:56:19Z |
| publishDate | 2023-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Robotics and AI |
| spelling | doaj.art-5ded23a3c05a4ded927bc2146b4cef772023-05-02T04:44:34ZengFrontiers Media S.A.Frontiers in Robotics and AI2296-91442023-05-011010.3389/frobt.2023.10767801076780AROS: Affordance Recognition with One-Shot Human StancesAbel Pacheco-Ortega0Walterio Mayol-Cuevas1Walterio Mayol-Cuevas2Visual Information Lab, Department of Computer Science, University of Bristol, Bristol, United KingdomVisual Information Lab, Department of Computer Science, University of Bristol, Bristol, United KingdomAmazon.com, Seattle, WA, United StatesWe present Affordance Recognition with One-Shot Human Stances (AROS), a one-shot learning approach that uses an explicit representation of interactions between highly articulated human poses and 3D scenes. The approach is one-shot since it does not require iterative training or retraining to add new affordance instances. Furthermore, only one or a small handful of examples of the target pose are needed to describe the interactions. Given a 3D mesh of a previously unseen scene, we can predict affordance locations that support the interactions and generate corresponding articulated 3D human bodies around them. We evaluate the performance of our approach on three public datasets of scanned real environments with varied degrees of noise. Through rigorous statistical analysis of crowdsourced evaluations, our results show that our one-shot approach is preferred up to 80% of the time over data-intensive baselines.https://www.frontiersin.org/articles/10.3389/frobt.2023.1076780/fullaffordance detectionscene understandinghuman interactionsvisual perceptionaffordances |
| spellingShingle | Abel Pacheco-Ortega Walterio Mayol-Cuevas Walterio Mayol-Cuevas AROS: Affordance Recognition with One-Shot Human Stances Frontiers in Robotics and AI affordance detection scene understanding human interactions visual perception affordances |
| title | AROS: Affordance Recognition with One-Shot Human Stances |
| title_full | AROS: Affordance Recognition with One-Shot Human Stances |
| title_fullStr | AROS: Affordance Recognition with One-Shot Human Stances |
| title_full_unstemmed | AROS: Affordance Recognition with One-Shot Human Stances |
| title_short | AROS: Affordance Recognition with One-Shot Human Stances |
| title_sort | aros affordance recognition with one shot human stances |
| topic | affordance detection scene understanding human interactions visual perception affordances |
| url | https://www.frontiersin.org/articles/10.3389/frobt.2023.1076780/full |
| work_keys_str_mv | AT abelpachecoortega arosaffordancerecognitionwithoneshothumanstances AT walteriomayolcuevas arosaffordancerecognitionwithoneshothumanstances AT walteriomayolcuevas arosaffordancerecognitionwithoneshothumanstances |