Long video question answering: A Matching-guided Attention Model
Authors:
- Weining WangWWWeining Wang
- Yan HuangYHYan Huang
- Liang WangLWLiang Wang
- 1 June 2020
- journal article
- research article
- Published by Elsevier in Pattern Recognition
- Vol. 102
Abstract
No abstract availableKeywords
Funding Information
- National Key Research and Development Program of China (2016YFB1001000, 2018AAA0100402)
- National Natural Science Foundation of China (61525306, 61633021, 61721004, 61420106015, 61806194, U1803261, 61976132)
This publication has 14 references indexed in Scilit:
- Blind image quality assessment via learnable attention-based poolingPattern Recognition, 2019
- Improving visual question answering using dropout and enhanced question encoderPattern Recognition, 2019
- MORAN: A Multi-Object Rectified Attention Network for scene text recognitionPattern Recognition, 2019
- Attention guided deep audio-face fusion for efficient speaker namingPattern Recognition, 2019
- Script identification in natural scene image and video frames using an attention based Convolutional-LSTM networkPattern Recognition, 2019
- Explicit ensemble attention learning for improving visual question answeringPattern Recognition Letters, 2018
- A Better Way to Attend: Attention With Trees for Video Question AnsweringIEEE Transactions on Image Processing, 2018
- FVQA: Fact-Based Visual Question AnsweringIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Unifying the Video and Question Attentions for Open-Ended Video Question AnsweringIEEE Transactions on Image Processing, 2017
- Uncovering the Temporal Context for Video Question AnsweringInternational Journal of Computer Vision, 2017