Please use this identifier to cite or link to this item:
Title: A Fine-Grained Spatial-Temporal Attention Model for Video Captioning
Authors: Liu, A.-A.
Qiu, Y.
Wong, Y. 
Su, Y.-T.
Kankanhalli, M. 
Keywords: Fine-grained
mask pooling
video captioning
Issue Date: 2018
Publisher: Institute of Electrical and Electronics Engineers Inc.
Citation: Liu, A.-A., Qiu, Y., Wong, Y., Su, Y.-T., Kankanhalli, M. (2018). A Fine-Grained Spatial-Temporal Attention Model for Video Captioning. IEEE Access 6 : 68463-68471. ScholarBank@NUS Repository.
Rights: Attribution-NonCommercial-NoDerivatives 4.0 International
Abstract: Attention mechanism has been extensively used in video captioning tasks, which enables further development of deeper visual understanding. However, most existing video captioning methods apply the attention mechanism on the frame level, which only model the temporal structure and generated words, but ignore the region-level spatial information that provides accurate visual features corresponding to the semantic content. In this paper, we propose a fine-grained spatial-temporal attention model (FSTA), and the spatial information of objects appearing in the video will be our main concern. In the proposed FSTA, we achieve the spatial-hard attention at a fine-grained region level of objects through the mask pooling module and compute the temporal soft attention by using a two-layer LSTM network with attention mechanism to generate sentences. We test the proposed model on two benchmark datasets, namely, MSVD and MSR-VTT. The results indicate that our proposed FSTA model can achieve competitive performance against the state of the arts on both datasets. © 2013 IEEE.
Source Title: IEEE Access
ISSN: 21693536
DOI: 10.1109/ACCESS.2018.2879642
Rights: Attribution-NonCommercial-NoDerivatives 4.0 International
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
10_1109_ACCESS_2018_2879642.pdf13.29 MBAdobe PDF




checked on May 28, 2023

Page view(s)

checked on May 25, 2023

Google ScholarTM



This item is licensed under a Creative Commons License Creative Commons