Multi-head attention-based two-stream EfficientNet for action recognition
CC BY
Lưu vào:
Tác giả chính: | , , |
---|---|
Định dạng: | Sách |
Ngôn ngữ: | English |
Nhà xuất bản: |
Springer
2023
|
Chủ đề: | |
Truy cập trực tuyến: | https://link.springer.com/article/10.1007/s00530-022-00961-3 https://dlib.phenikaa-uni.edu.vn/handle/PNK/7352 |
Từ khóa: |
Thêm từ khóa
Không có từ khóa, Hãy là người đầu tiên đánh dấu biểu ghi này!
|
id |
oai:localhost:PNK-7352 |
---|---|
record_format |
dspace |
spelling |
oai:localhost:PNK-73522023-03-31T01:20:48Z Multi-head attention-based two-stream EfficientNet for action recognition Aihua, Zhou Yujun, Ma Wanting, Ji Multi-head Attention-based Two-stream EfficientNet MAT-EffNet EfficientNet CC BY Recent years have witnessed the popularity of using two-stream convolutional neural networks for action recognition. However, existing two-stream convolutional neural network-based action recognition approaches are incapable of distinguishing some roughly similar actions in videos such as sneezing and yawning. To solve this problem, we propose a Multi-head Attention-based Two-stream EfficientNet (MAT-EffNet) for action recognition, which can take advantage of the efficient feature extraction of EfficientNet. The proposed network consists of two streams (i.e., a spatial stream and a temporal stream), which first extract the spatial and temporal features from consecutive frames by using EfficientNet. 2023-03-31T01:20:48Z 2023-03-31T01:20:48Z 2023 Book https://link.springer.com/article/10.1007/s00530-022-00961-3 https://dlib.phenikaa-uni.edu.vn/handle/PNK/7352 en application/pdf Springer |
institution |
Digital Phenikaa |
collection |
Digital Phenikaa |
language |
English |
topic |
Multi-head Attention-based Two-stream EfficientNet MAT-EffNet EfficientNet |
spellingShingle |
Multi-head Attention-based Two-stream EfficientNet MAT-EffNet EfficientNet Aihua, Zhou Yujun, Ma Wanting, Ji Multi-head attention-based two-stream EfficientNet for action recognition |
description |
CC BY |
format |
Book |
author |
Aihua, Zhou Yujun, Ma Wanting, Ji |
author_facet |
Aihua, Zhou Yujun, Ma Wanting, Ji |
author_sort |
Aihua, Zhou |
title |
Multi-head attention-based two-stream EfficientNet for action recognition |
title_short |
Multi-head attention-based two-stream EfficientNet for action recognition |
title_full |
Multi-head attention-based two-stream EfficientNet for action recognition |
title_fullStr |
Multi-head attention-based two-stream EfficientNet for action recognition |
title_full_unstemmed |
Multi-head attention-based two-stream EfficientNet for action recognition |
title_sort |
multi-head attention-based two-stream efficientnet for action recognition |
publisher |
Springer |
publishDate |
2023 |
url |
https://link.springer.com/article/10.1007/s00530-022-00961-3 https://dlib.phenikaa-uni.edu.vn/handle/PNK/7352 |
_version_ |
1761912523406180352 |
score |
8.891145 |