Skip to main content
Springer Nature Link
Log in

Ad-hoc Video Search Improved by the Word Sense Filtering of Query Terms

  • Conference paper
  • First Online:
Information Retrieval Technology (AIRS 2018)

Part of the book series: Lecture Notes in Computer Science ((LNISA,volume 11292))

Included in the following conference series:

  • 477 Accesses

Abstract

The performances of an ad-hoc video search (AVS) task can only be improved when the video processing for analyzing video contents and the linguistic processing for interpreting natural language queries are nicely combined. Among the several issues associated with this challenging task, this paper particularly focuses on the sense disambiguation/filtering (WSD/WSF) of the terms contained in a search query. We propose WSD/WSF methods which employ distributed sense representations, and discuss their efficacy in improving the performance of an AVS system which makes full use of a large bank of visual concept classifiers. The application of a WSD/WSF method is crucial, as each visual concept classifier is linked with the lexical concept denoted by a word sense. The results are generally promising, outperforming not only a baseline query processing method that only considers the polysemy of a query term but also a strong WSD baseline method.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    https://trecvid.nist.gov/.

  2. 2.

    A WordNet synset denotes a lexical concept. It is defined by a set of synonymous word senses. A word, more precisely a word form, generally has multiple senses and each sense denotes a unique synset.

  3. 3.

    Refer to [9] for the list of employed classifiers.

  4. 4.

    We employed the MS COCO dataset available at http://cocodataset.org.

  5. 5.

    https://code.google.com/archive/p/word2vec/.

  6. 6.

    The official evaluation metrics adopted by TRECVID AVS is a variant of usual mAP.

  7. 7.

    As the number of queries in the TRECVID AVS task is as small as 30, the WSD accuracies by the presented methods are quite unstable. We could not observe any statistical significance. However the DistSim method slightly outperformed two other methods in precision: 0.892 (DistSim) to 0.890 (MFS) and 0.888 (SimSum).

References

  1. Awad, G., et al.: Trecvid 2017: evaluating ad-hoc and instance video search, events detection, video captioning and hyperlinking. In: Proceedings of TRECVID 2017. NIST, USA (2017)

    Google Scholar 

  2. Deng, J., Dong, W., Socher, R., jia Li, L., Li, K., Fei-fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR (2009)

    Google Scholar 

  3. Inoue, N., Shinoda, K.: Semantic indexing for large-scale video retrieval. ITE Trans. Media Technol. Appl. 4(3), 209–217 (2016). https://doi.org/10.3169/mta.4.209

    Article  Google Scholar 

  4. Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 2, NIPS 2013, pp. 3111–3119. Curran Associates Inc., USA (2013)

    Google Scholar 

  5. Miller, G.A., Fellbaum, C.: Wordnet then and now. Lang. Resour. Eval. 41(2), 209–214 (2007). https://doi.org/10.1007/s10579-007-9044-6

    Article  Google Scholar 

  6. Navigli, R.: Word sense disambiguation: a survey. ACM Comput. Surv. 41(2), 1–69 (2009)

    Article  Google Scholar 

  7. Rothe, S., Schütze, H.: Autoextend: combining word embeddings with semantic resources. Comput. Linguist. 43(3), 593–617 (2017)

    Article  MathSciNet  Google Scholar 

  8. Snow, R., Prakash, S., Jurafsky, D., Ng, A.Y.: Learning to merge word senses. In: Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL) (2007)

    Google Scholar 

  9. Ueki, K., Hirakawa, K., Kikuchi, K., Ogawa, T., Kobayashi, T.: Waseda\(\_\)meisei at trecvid 2017: Ad-hoc video search. In: 2017 TREC Video Retrieval Evaluation Notebook Papers (2017)

    Google Scholar 

Download references

Acknowledgment

The present work was partially supported by JSPS KAKENHI Grants numbers 15K00249, 17H01831, and 18K11362, and the Kayamori Foundation of Informational Science Advancement.

Author information

Authors and Affiliations

  1. Waseda University, Tokyo, Japan

    Koji Hirakawa, Kotaro Kikuchi, Kazuya Ueki, Tetsunori Kobayashi & Yoshihiko Hayashi

  2. Meisei University, Hino, Japan

    Kazuya Ueki

Authors
  1. Koji Hirakawa
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kotaro Kikuchi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Kazuya Ueki
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Tetsunori Kobayashi
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yoshihiko Hayashi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yoshihiko Hayashi .

Editor information

Editors and Affiliations

  1. National Taiwan Normal University, Taipei, Taiwan

    Yuen-Hsien Tseng

  2. Waseda University, Tokyo, Japan

    Tetsuya Sakai

  3. School of Information Systems, Singapore Management University, Singapore, Singapore

    Jing Jiang

  4. Academia Sinica, Taipei, Taiwan

    Lun-Wei Ku

  5. Huawei Research America, Champaign, IL, USA

    Dae Hoon Park

  6. National Chiayi University, Chiayi City, Taiwan

    Jui-Feng Yeh

  7. Yuan Ze University, Taoyuan City, Taiwan

    Liang-Chih Yu

  8. National Central University, Taoyuan City, Taiwan

    Lung-Hao Lee

  9. National Taiwan Normal University, Taipei City, Taiwan

    Zhi-Hong Chen

Rights and permissions

Reprints and permissions

Copyright information

© 2018 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Hirakawa, K., Kikuchi, K., Ueki, K., Kobayashi, T., Hayashi, Y. (2018). Ad-hoc Video Search Improved by the Word Sense Filtering of Query Terms. In: Tseng, YH., et al. Information Retrieval Technology. AIRS 2018. Lecture Notes in Computer Science(), vol 11292. Springer, Cham. https://doi.org/10.1007/978-3-030-03520-4_15

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-03520-4_15

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-03519-8

  • Online ISBN: 978-3-030-03520-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics