Semantic-filtered Soft-Split-Aware video captioning with audio-augmented feature
Automatic video description, or video captioning, is a challenging yet much attractive task. It aims to combine video with text. Multiple methods have been proposed based on neural networks, utilizing Convolutional Neural Networks (CNN) to extract features, and Recurrent Neural Networks (RNN) to enc...
Saved in:
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/151341 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-151341 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1513412021-07-09T01:29:56Z Semantic-filtered Soft-Split-Aware video captioning with audio-augmented feature Xu, Yuecong Yang, Jianfei Mao, Kezhi School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Video Captioning Long Short-term Memory Automatic video description, or video captioning, is a challenging yet much attractive task. It aims to combine video with text. Multiple methods have been proposed based on neural networks, utilizing Convolutional Neural Networks (CNN) to extract features, and Recurrent Neural Networks (RNN) to encode and decode videos to generate descriptions. Previously, a number of methods used in video captioning task are motivated by image captioning approaches. However, videos carry much more information than images. This increases the difficulty of video captioning task. Current methods commonly lack the ability to utilize the additional information provided by videos, especially the semantic and structural information of the videos. To address the above shortcoming, we propose a Semantic-Filtered Soft-Split-Aware-Gated LSTM (SF-SSAG-LSTM) model, that would improve video captioning quality by combining semantic concepts with audio-augmented feature extracted from input videos, while understanding the underlying structure of input videos. In the experiments, we quantitatively evaluate the performance of our model which matches other prominent methods on three benchmark datasets. We also qualitatively examine the result of our model, and show that our generated descriptions are more detailed and logical. 2021-07-09T01:29:56Z 2021-07-09T01:29:56Z 2019 Journal Article Xu, Y., Yang, J. & Mao, K. (2019). Semantic-filtered Soft-Split-Aware video captioning with audio-augmented feature. Neurocomputing, 357, 24-35. https://dx.doi.org/10.1016/j.neucom.2019.05.027 0925-2312 0000-0002-8075-0439 https://hdl.handle.net/10356/151341 10.1016/j.neucom.2019.05.027 2-s2.0-85065823631 357 24 35 en Neurocomputing © 2019 Elsevier B.V. All rights reserved. |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Electrical and electronic engineering Video Captioning Long Short-term Memory |
spellingShingle |
Engineering::Electrical and electronic engineering Video Captioning Long Short-term Memory Xu, Yuecong Yang, Jianfei Mao, Kezhi Semantic-filtered Soft-Split-Aware video captioning with audio-augmented feature |
description |
Automatic video description, or video captioning, is a challenging yet much attractive task. It aims to combine video with text. Multiple methods have been proposed based on neural networks, utilizing Convolutional Neural Networks (CNN) to extract features, and Recurrent Neural Networks (RNN) to encode and decode videos to generate descriptions. Previously, a number of methods used in video captioning task are motivated by image captioning approaches. However, videos carry much more information than images. This increases the difficulty of video captioning task. Current methods commonly lack the ability to utilize the additional information provided by videos, especially the semantic and structural information of the videos. To address the above shortcoming, we propose a Semantic-Filtered Soft-Split-Aware-Gated LSTM (SF-SSAG-LSTM) model, that would improve video captioning quality by combining semantic concepts with audio-augmented feature extracted from input videos, while understanding the underlying structure of input videos. In the experiments, we quantitatively evaluate the performance of our model which matches other prominent methods on three benchmark datasets. We also qualitatively examine the result of our model, and show that our generated descriptions are more detailed and logical. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Xu, Yuecong Yang, Jianfei Mao, Kezhi |
format |
Article |
author |
Xu, Yuecong Yang, Jianfei Mao, Kezhi |
author_sort |
Xu, Yuecong |
title |
Semantic-filtered Soft-Split-Aware video captioning with audio-augmented feature |
title_short |
Semantic-filtered Soft-Split-Aware video captioning with audio-augmented feature |
title_full |
Semantic-filtered Soft-Split-Aware video captioning with audio-augmented feature |
title_fullStr |
Semantic-filtered Soft-Split-Aware video captioning with audio-augmented feature |
title_full_unstemmed |
Semantic-filtered Soft-Split-Aware video captioning with audio-augmented feature |
title_sort |
semantic-filtered soft-split-aware video captioning with audio-augmented feature |
publishDate |
2021 |
url |
https://hdl.handle.net/10356/151341 |
_version_ |
1705151338565861376 |