Conference proceeding
Fully Convolutional Video Captioning with Coarse-to-Fine and Inherited Attention
THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, Vol.33(1), pp.8271-8278
AAAI Conference on Artificial Intelligence
07/17/2019
DOI: 10.1609/aaai.v33i01.33018271
Abstract
Automatically generating natural language description for video is an extremely complicated and challenging task. To tackle the obstacles of traditional LSTM-based model for video captioning, we propose a novel architecture to generate the optimal descriptions for videos, which focuses on constructing a new network structure that can generate sentences superior to the basic model with LSTM, and establishing special attention mechanisms that can provide more useful visual information for caption generation. This scheme discards the traditional LSTM, and exploits the fully convolutional network with coarse-to-fine and inherited attention designed according to the characteristics of fully convolutional structure. Our model cannot only outperform the basic LSTM-based model, but also achieve the comparable performance with those of state-of-the-art methods.
Details
- Title: Subtitle
- Fully Convolutional Video Captioning with Coarse-to-Fine and Inherited Attention
- Creators
- Kuncheng Fang - Fudan UniversityLian Zhou - Fudan UniversityCheng Jin - Fudan UniversityYuejie Zhang - Fudan UniversityKangnian Weng - Shanghai University of Finance and EconomicsTao Zhang - Shanghai University of Finance and EconomicsWeiguo Fan - University of Iowa
- Resource Type
- Conference proceeding
- Publication Details
- THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, Vol.33(1), pp.8271-8278
- Publisher
- Assoc Advancement Artificial Intelligence
- Series
- AAAI Conference on Artificial Intelligence
- DOI
- 10.1609/aaai.v33i01.33018271
- ISSN
- 2159-5399
- eISSN
- 2374-3468
- Number of pages
- 8
- Grant note
- 61572140; 61672165 / National Natural Science Foundation of China; National Natural Science Foundation of China (NSFC) 17DZ1100504; 16JC1420401; 16511104704 / Shanghai Municipal RD Foundation Henry Tippie Endowed Chair Fund from the University of Iowa
- Language
- English
- Date published
- 07/17/2019
- Academic Unit
- Business Analytics
- Record Identifier
- 9984380534602771
Metrics
3 Record Views