Paper
30 June 2021 Video captioning based on multi-feature fusion with object awareness
Lijuan Zhou, Tao Liu, Changyong Niu
Author Affiliations +
Proceedings Volume 11878, Thirteenth International Conference on Digital Image Processing (ICDIP 2021); 118780D (2021) https://doi.org/10.1117/12.2601115
Event: Thirteenth International Conference on Digital Image Processing, 2021, Singapore, Singapore
Abstract
This paper proposes a novel method to utilize three source features for video captioning. It fuses global video features with local object and regional features to model the relationships among objects and their motions and applies object tags instead of visual features to guide the generation of descriptions. Specifically, Multi-feature is firstly extracted by pretrained models and treated as separate inputs alongside video frames. Secondly, an object awareness attention block is designed to fuse the different features information and to learn a joint video representation which has both visual and linguistic semantics. Experiments on MSVD and MSR-VTT datasets have shown the effectiveness of the proposed method, and the ablation studies have verified the contribution of each component.
© (2021) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Lijuan Zhou, Tao Liu, and Changyong Niu "Video captioning based on multi-feature fusion with object awareness", Proc. SPIE 11878, Thirteenth International Conference on Digital Image Processing (ICDIP 2021), 118780D (30 June 2021); https://doi.org/10.1117/12.2601115
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
Back to Top