›› 2017, Vol. 32 ›› Issue (4): 738-748.doi: 10.1007/s11390-017-1755-6

Special Issue: Artificial Intelligence and Pattern Recognition

• Special Issue on Deep Learning • Previous Articles     Next Articles

Deep Multimodal Reinforcement Network with Contextually Guided Recurrent Attention for Image Question Answering

Ai-Wen Jiang1, Member, CCF, Bo Liu2, Ming-Wen Wang1,*, Senior Member, CCF   

  1. 1 College of Computer and Information Engineering, Jiangxi Normal University, Nanchang 330022, China;
    2 College of Computer Science and Software Engineering, Auburn University, Auburn, AL 36849, U.S.A
  • Received:2016-12-19 Revised:2017-05-26 Online:2017-07-05 Published:2017-07-05
  • Contact: Ming-Wen Wang E-mail:mwwang@jxnu.edu.cn
  • Supported by:

    This work was supported by the National Natural Science Foundation of China under Grant Nos. 61365002 and 61462045, and the Science and Technology Project of the Education Department of Jiangxi Province of China under Grant No. GJJ150350.

Image question answering (IQA) has emerged as a promising interdisciplinary topic in computer vision and natural language processing fields. In this paper, we propose a contextually guided recurrent attention model for solving the IQA issues. It is a deep reinforcement learning based multimodal recurrent neural network. Based on compositional contextual information, it recurrently decides where to look using reinforcement learning strategy. Different from traditional "static" soft attention, it is deemed as a kind of "dynamic" attention whose objective is designed based on reinforcement rewards purposefully towards IQA. The finally learned compositional information incorporates both global context and local informative details, which is demonstrated to benefit for generating answers. The proposed method is compared with several state-of-the-art methods on two public IQA datasets, including COCO-QA and VQA from dataset MS COCO. The experimental results demonstrate that our proposed model outperforms those methods and achieves better performance.

[1] Ren M Y, Kiros R, Zemel R. Image question answering:A visual semantic embedding model and a new dataset. arXiv:1505.02074, 2015. https://arxiv.org/abs/1505.02074v1, June 2017.

[2] Gao H Y, Mao J H, Zhou J, Huang Z H, Wang L, Xu W. Are you talking to a machine? Dataset and methods for multilingual image question answering. arXiv:1505.05612, 2015. https://arxiv.org/abs/1505.05612, June 2017.

[3] Antol S, Agrawal A, Lu J S, Mitchell M, Batra D, Zitnick L, Parikh D. VQA:Visual question answering. In Proc. IEEE Int. Conf. Computer Vision, December 2015, pp.2425-2433.

[4] Malinowski M, Rohrbach M, Fritz M. Ask your neurons:A deep learning approach to visual question answering. arXiv:1605.02697, 2016. https://arxiv.org/abs/1605.02697, June 2017.

[5] Xu K, Ba J, Kiros R, Cho K, Courville A, Salakhutdinov R, Zemel R, Bengio Y. Show, attend and tell:Neural image caption generation with visual attention. In Proc. the 32nd IEEE Int. Conf. Machine Learning, February 2015, pp.2048-2057.

[6] Yang Z C, He X D, Gao J F, Deng L, Smola A. Stacked attention networks for image question answering. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2016, pp.21-29.

[7] Xu H J, Saenko K. Ask, attend and answer:Exploring question-guided spatial attention for visual question answering. arXiv:1511.05234, 2015. https://arxiv. org/abs/1511.05234, June 2017.

[8] Chen K, Wang J, Chen L C, Gao H Y, Xu W, Nevatia R. ABC-CNN:An attention based convolutional neural network for visual question answering. arXiv:1511.05960, 2015. https://arxiv.org/abs/1511.05960, June 2017.

[9] Shih K J, Singh S, Hoiem D. Where to look:Focus regions for visual question answering. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2016, pp.4613-4621.

[10] Zhu Y K, Groth O, Bernstein M, Li F F. Visual7W:Grounded question answering in images. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2016, pp.4995-5004.

[11] Ilievski I, Yan S C, Feng J S. A focused dynamic attention model for visual question answering. arXiv:1604.01485, 2016. https://arxiv.org/abs/1604.01485, June 2017.

[12] Kumar A, Irsoy O, Ondruska P, Iyyer M, Bradbury J, Gulrajani I, Zhong V, Paulus R, Socher R. Ask me anything:Dynamic memory networks for natural language processing. In Proc. the 33rd Int. Conf. Machine Learning, June 2016, pp.1378-1387.

[13] Xiong C M, Merity S, Socher R. Dynamic memory networks for visual and textual question answering. In Proc. the 33rd Int. Conf. Machine Learning, June 2016, pp.2397-2406.

[14] Lu J S, Yang JW, Batra D, Parikh D. Hierarchical questionimage co-attention for visual question answering. In Proc. Advances in Neural Information Processing System, Dec. 2016.

[15] Fukui A, Park D H, Yang D, Rohrbach A, Darrell T, Rohrbach M. Multimodal compact bilinear pooling for visual question answering and visual grounding. arXiv:1606.01847, 2016. https://arxiv.org/abs/1606.01847, June 2017.

[16] Noh H, Seo P H, Han B. Image question answering using convolutional neural network with dynamic parameter prediction. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2016, pp.30-38.

[17] Kim J H, Lee S W, Kwak D H, Heo M, Kim J, Ha J W, Zhang B T. Multimodal residual learning for visual QA. In Proc. the 30th Conf. Neural Information Processing System, Dec. 2016.

[18] Andreas J, Rohrbach M, Darrell T, Klein D. Neural module networks. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2016, pp.39-48.

[19] Wang P, Wu Q, Shen C H, van den Hengel A, Dick A. Explicit knowledge-based reasoning for visual question answering. arXiv:1511.02570, 2015. https://arxiv.org/abs/1511.02570v2, June 2017.

[20] Ma L, Lu Z D, Li H. Learning to answer questions from image using convolutional neural network. In Proc. the 30th AAAI Conf. Artificial Intelligence, March 2016, pp.3567-3573.

[21] Mnih V, Heess N, Graves A, Kavukcuoglu K. Recurrent models of visual attention. In Proc. Advances in Neural Information Processing Systems, Dec. 2014.

[22] Ba J, Mnih V, Kavukcuoglu K. Multiple object recognition with visual attention. arXiv:1412.7755, 2015. https://arxiv.org/abs/1412.7755, June 2017.

[23] Li J N, Wei Y C, Liang X D, Dong J, Xu T F, Feng J S, Yan S C. Attentive contexts for object detection. arXiv:1603.07415, 2016. https://arxiv.org/abs/1603.07415, June 2017.

[24] Chung K, Gulcehre C, Cho K, Bengio Y. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv:1412.3555, 2014. https://arxiv.org/abs/14-12.3555, June 2017.

[25] Mikolov T, Chen K, Corrado G, Dean J. Efficient estimation of word representations in vector space. arXiv:1301.3781, 2013. https://arxiv.org/abs/1301.3781, June 2017.

[26] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556, 2015. https://arxiv.org/abs/1409.1556, June 2017.

[27] Williams R J. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 1992, 8(3/4):229-256.

[28] Kiros R, Zhu Y K, Salakhutdinov R, Zemel R, Torralba A, Urtasun R, Fidler S. Skip-thought vectors. arXiv:1506.06726, 2015. https://arxiv.org/abs/1506.06726, June 2017.

[29] Zhou B L, Tian Y D, Sukhbaatar S, Szlam A, Fergus R. Simple baseline for visual question answering. arXiv:1512.02167, 2015. https://arxiv.org/abs/1512.02167, June 2017.

[30] Malinowski M, Fritz M. A multi-world approach to question answering about real-world scenes based on uncertain input. In Proc. the 27th Int. Conf. Neural Information Processing Systems, Dec. 2014, pp.1682-1690.

[31] Wu Z B, Palmer M. Verbs semantics and lexical selection. In Proc. the 32nd Annual Meeting on Association for Computational Linguistics, June 1994, pp.133-138.

[32] Miller G A. WordNet:A lexical database for English. Communications of the ACM, 1995, 38(11):39-41.

[33] Szegedy C, Liu W, Jia Y Q, Sermanet P, Reed S E, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions. arXiv:1409.4842, 2014. https://arxiv.org/abs/1409.4842, June 2017.

[34] He K M, Zhang X Y, Ren S Q, Sun J. Deep residual learning for image recognition. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2016, pp.770-778.
No related articles found!
Full text



[1] Liu Mingye; Hong Enyu;. Some Covering Problems and Their Solutions in Automatic Logic Synthesis Systems[J]. , 1986, 1(2): 83 -92 .
[2] Chen Shihua;. On the Structure of (Weak) Inverses of an (Weakly) Invertible Finite Automaton[J]. , 1986, 1(3): 92 -100 .
[3] Gao Qingshi; Zhang Xiang; Yang Shufan; Chen Shuqing;. Vector Computer 757[J]. , 1986, 1(3): 1 -14 .
[4] Chen Zhaoxiong; Gao Qingshi;. A Substitution Based Model for the Implementation of PROLOG——The Design and Implementation of LPROLOG[J]. , 1986, 1(4): 17 -26 .
[5] Huang Heyan;. A Parallel Implementation Model of HPARLOG[J]. , 1986, 1(4): 27 -38 .
[6] Min Yinghua; Han Zhide;. A Built-in Test Pattern Generator[J]. , 1986, 1(4): 62 -74 .
[7] Tang Tonggao; Zhao Zhaokeng;. Stack Method in Program Semantics[J]. , 1987, 2(1): 51 -63 .
[8] Min Yinghua;. Easy Test Generation PLAs[J]. , 1987, 2(1): 72 -80 .
[9] Zhu Hong;. Some Mathematical Properties of the Functional Programming Language FP[J]. , 1987, 2(3): 202 -216 .
[10] Li Minghui;. CAD System of Microprogrammed Digital Systems[J]. , 1987, 2(3): 226 -235 .

ISSN 1000-9000(Print)

CN 11-2296/TP

Editorial Board
Author Guidelines
Journal of Computer Science and Technology
Institute of Computing Technology, Chinese Academy of Sciences
P.O. Box 2704, Beijing 100190 P.R. China
E-mail: jcst@ict.ac.cn
  Copyright ©2015 JCST, All Rights Reserved