Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ arXiv.org e-Print Ar...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
arXiv.org e-Print Archive
Other literature type . Preprint . 2016
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
http://arxiv.org/pdf/1611.0997...
Conference object
Data sources: UnpayWall
https://doi.org/10.48550/arxiv...
Article . 2016
License: arXiv Non-Exclusive Distribution
Data sources: Datacite
https://doi.org/10.1109/cvpr.2...
Conference object . 2017 . Peer-reviewed
Data sources: Crossref
versions View all 4 versions
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Modeling Relationships in Referential Expressions with Compositional Modular Networks

Authors: Hu, Ronghang; Rohrbach, Marcus; Andreas, Jacob; Darrell, Trevor; Saenko, Kate;

Modeling Relationships in Referential Expressions with Compositional Modular Networks

Abstract

People often refer to entities in an image in terms of their relationships with other entities. For example, "the black cat sitting under the table" refers to both a "black cat" entity and its relationship with another "table" entity. Understanding these relationships is essential for interpreting and grounding such natural language expressions. Most prior work focuses on either grounding entire referential expressions holistically to one region, or localizing relationships based on a fixed set of categories. In this paper we instead present a modular deep architecture capable of analyzing referential expressions into their component parts, identifying entities and relationships mentioned in the input expression and grounding them all in the scene. We call this approach Compositional Modular Networks (CMNs): a novel architecture that learns linguistic analysis and visual inference end-to-end. Our approach is built around two types of neural modules that inspect local regions and pairwise interactions between regions. We evaluate CMNs on multiple referential expression datasets, outperforming state-of-the-art approaches on all tasks.

Subjects by Vocabulary

Microsoft Academic Graph classification: Referring expression Computer science business.industry Inference Modular design computer.software_genre Expression (mathematics) Set (abstract data type) Component (UML) Artificial intelligence business computer Natural language processing Natural language

Keywords

FOS: Computer and information sciences, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition

33 references, page 1 of 4

[1] M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G. S. Corrado, A. Davis, J. Dean, M. Devin, S. Ghemawat, I. Goodfellow, A. Harp, G. Irving, M. Isard, Y. Jia, R. Jozefowicz, L. Kaiser, M. Kudlur, J. Levenberg, D. Mane´, R. Monga, S. Moore, D. Murray, C. Olah, M. Schuster, J. Shlens, B. Steiner, I. Sutskever, K. Talwar, P. Tucker, V. Vanhoucke, V. Vasudevan, F. Vie´gas, O. Vinyals, P. Warden, M. Wattenberg, M. Wicke, Y. Yu, and X. Zheng. TensorFlow: Large-scale machine learning on heterogeneous systems. arXiv:1603.04467, 2016. 5

[2] J. Andreas, M. Rohrbach, T. Darrell, and D. Klein. Learning to compose neural networks for question answering. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2016. 2

[3] J. Andreas, M. Rohrbach, T. Darrell, and D. Klein. Neural module networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. 2, 5

[4] P. Arbela´ez, J. Pont-Tuset, J. Barron, F. Marques, and J. Malik. Multiscale combinatorial grouping. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014. 2

[5] J. Ba, V. Mnih, and K. Kavukcuoglu. Multiple object recognition with visual attention. In Proceedings of the International Conference on Learning Representations (ICLR), 2015. 4

[6] J. Dai, Y. Li, K. He, and J. Sun. R-fcn: Object detection via region-based fully convolutional networks. In Advances in Neural Information Processing Systems (NIPS), 2016. 1

[7] A. Fukui, D. H. Park, D. Yang, A. Rohrbach, T. Darrell, and M. Rohrbach. Multimodal compact bilinear pooling for visual question answering and visual grounding. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2016. 2

[8] R. Girshick, J. Donahue, T. Darrell, and J. Malik. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014. 1, 2

[9] X. Glorot and Y. Bengio. Understanding the difficulty of training deep feedforward neural networks. In Aistats, volume 9, pages 249-256, 2010. 5

[10] R. Hu, M. Rohrbach, and T. Darrell. Segmentation from natural language expressions. In Proceedings of the European Conference on Computer Vision (ECCV), 2016. 6

  • BIP!
    Impact byBIP!
    citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    164
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Top 1%
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Top 1%
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Top 1%
  • citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    164
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Top 1%
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Top 1%
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Top 1%
    Powered byBIP!BIP!
Powered by OpenAIRE graph
Found an issue? Give us feedback
citations
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
164
Top 1%
Top 1%
Top 1%
Green