Stacked encoder–decoder transformer with boundary smoothing for action segmentationopen access
- Authors
- Kim, G.-H.; Kim, Eunwoo
- Issue Date
- Dec-2022
- Publisher
- John Wiley and Sons Inc
- Keywords
- artificial intelligence; image and vision processing and display technology
- Citation
- Electronics Letters, v.58, no.25, pp 972 - 974
- Pages
- 3
- Journal Title
- Electronics Letters
- Volume
- 58
- Number
- 25
- Start Page
- 972
- End Page
- 974
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/61136
- DOI
- 10.1049/ell2.12678
- ISSN
- 0013-5194
1350-911X
- 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. © 2022 The Authors. Electronics Letters published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.
- Files in This Item
-
- Appears in
Collections - College of Software > School of Computer Science and Engineering > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/61136)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.