We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Stacked encoder–decoder transformer with boundary smoothing for action segmentation.
- Authors
Kim, Gyeong‐hyeon; Kim, Eunwoo
- Abstract
In this work, a new stacked encoder–decoder transformer (SEDT) model is proposed for action segmentation. SEDT is composed of a series of encoder–decoder modules, each of which consists of an encoder with self‐attention layers and a decoder with cross‐attention layers. By adding an encoder with self‐attention before every decoder, it preserves local information along with global information. The proposed encoder–decoder pair also prevents the accumulation of errors that occur when features are propagated through decoders. Moreover, the approach performs boundary smoothing in order to handle ambiguous action boundaries. Experimental results for two popular benchmark datasets, "GTEA" and "50 Salads", show that the proposed model is more effective in performance than existing temporal convolutional network based models and the attention‐based model, ASFormer.
- Subjects
CONVOLUTIONAL neural networks; ARTIFICIAL intelligence
- Publication
Electronics Letters (Wiley-Blackwell), 2022, Vol 58, Issue 25, p972
- ISSN
0013-5194
- Publication type
Article
- DOI
10.1049/ell2.12678