Semantic compositional networks for visual captioning

Zhe Gan, Chuang Gan, Xiaodong He, Yunchen Pu, Kenneth Tran, Jianfeng Gao, Lawrence Carin, Li Deng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

135 Scopus citations

Abstract

A Semantic Compositional Network (SCN) is developed for image captioning, in which semantic concepts (i.e., tags) are detected from the image, and the probability of each tag is used to compose the parameters in a long short-term memory (LSTM) network. The SCN extends each weight matrix of the LSTM to an ensemble of tag-dependent weight matrices. The degree to which each member of the ensemble is used to generate an image caption is tied to the image-dependent probability of the corresponding tag. In addition to captioning images, we also extend the SCN to generate captions for video clips. We qualitatively analyze semantic composition in SCNs, and quantitatively evaluate the algorithm on three benchmark datasets: COCO, Flickr30k, and Youtube2Text. Experimental results show that the proposed method significantly outperforms prior state-of-the-art approaches, across multiple evaluation metrics.
Original languageEnglish (US)
Title of host publicationProceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1141-1150
Number of pages10
ISBN (Print)9781538604571
DOIs
StatePublished - Nov 6 2017
Externally publishedYes

Fingerprint Dive into the research topics of 'Semantic compositional networks for visual captioning'. Together they form a unique fingerprint.

Cite this