Advertisement

Anchor Shot Detection with Deep Neural Network

  • Bailan Feng
  • Jinfeng Bai
  • Zhineng Chen
  • Xiangsheng Huang
  • Bo Xu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8879)

Abstract

Anchor Shot Detection (ASD) is a key step for segmenting news videos into stories. However, the existing ASD methods are either channel-related or channel-limited which could not satisfy the requirement for achieving effective management of large-scale broadcast news videos. Considering the variety and diversity of large-scale news videos and channels, in this paper we propose a universal scheme based on deep neural network for anchor shot detection (DNN_ASD). Firstly, DNN_ASD consists of a training procedure of deep neural network to learn the appropriate anchor shot detector. Secondly, accompanied with imbalanced sampling strategy and face-assist verification, a universal scheme of anchor shot detection for large-scale news videos and channels is available. Parallel to this, the width and depth of neural network and the transfer ability are empirically discussed respectively as well. Encouraging experimental results on news videos from 30 TV channels demonstrate the effectiveness of the proposed scheme, as well as its superiority on transfer ability over traditional ASD methods.

Keywords

Anchor Shot Detection Deep Neural Network Imbalanced Sampling Strategy 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Hsu, W.H., Kenney, L.S., Chang, S.F., Franz, M., Smith, J.: Columbia-IBM News Video Story Segmentation in TRECVID. In: Proc. ACM CIVR, pp. 1–11 (2005)Google Scholar
  2. 2.
    Xu, S., Feng, B.L., Chen, Z.N., Xu, B.: A General Framework of Video Segmentation to Logical Unit based on Conditional Random Fields. In: Proc. ACM ICMR, pp. 247–254 (2013)Google Scholar
  3. 3.
    Feng, B.L., Chen, Z.N., Zheng, R., Xu, B.: Multiple Style Exploration for Story Unit Segmentation of Broadcast News Video. Multimedia Systems 20(4), 347–361 (2014)CrossRefGoogle Scholar
  4. 4.
    Smoliar, S.W., Zhang, H.J., Tao, S.Y., Gong, Y.: Automatic Parsing and Indexing of News Video. Multimedia Systems 2(6), 256–265 (1995)CrossRefGoogle Scholar
  5. 5.
    Hanjalic, A., Lagendijk, R.L., Biemond, J.: Semi-Automatic News Analysis, Indexing and Classification System based on Topics Preselection. In: Proc. of SPIE: Electronic Imaging: Storage and Retrieval of Image and Video Databases, San Jose, CA (1999)Google Scholar
  6. 6.
    Liu, Z., Huang, Q.: Adaptive Anchor Detection using On-line Trained Audio/Visual Model. In: Proc. of SPIE, Storage and Retrieval for Media Database (2000)Google Scholar
  7. 7.
    Santo, M.D., Foggia, P., Percannella, G., Sansone, C., Vento, M.: An Unsupervised Algorithm for Anchor Shot Detection. In: Proc. IEEE ICPR, pp. 1238–1241 (2006)Google Scholar
  8. 8.
    Gao, X., Tang, X.: Unsupervised Video-Shot Segmentation and Model-Free Anchorperson Detection for News Video Story Parsing. IEEE Trans. Circuits and System for Video Technology 12(9), 765–776 (2002)CrossRefGoogle Scholar
  9. 9.
    Hsu, W., Chang, S.F., Huang, C.W., Kennedy, L., Lin, C.Y., Iyengar, G.: Discovery and Fusion of Salient Multi-Modal Features towards News Story Segmentation. In: Proc. of SPIE: Symposium on Electronic Imaging: Storage and Retrieval of Image/Video Database, San Jose, USA (2004)Google Scholar
  10. 10.
    Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution Gray-scale and Rotation Invariant Texture Classification with Local Binary Patterns. IEEE Trans. Pattern Analysis and Machine Intelligence 24(7), 971–987 (2002)CrossRefGoogle Scholar
  11. 11.
    Tesic, J., Natsev, A., Xie, L., Smith, J.R.: Data Modeling Strategy for Imbalanced Learning in Visual Search. In: Proc. IEEE ICME, pp. 1990–1993 (2007)Google Scholar
  12. 12.
    Liu, C.L., Sako, H., Fujisawa, H.: Handwritten Chinese Character Recognition: Alternatives to Nonlinear Normalization. In: Proc. ICDAR, pp. 524–528 (2003)Google Scholar
  13. 13.
    Bai, J., Chen, Z., Feng, B., Xu, B.: Chinese Image Character Recognition Using DNN and Machine Simulated Training Samples. In: Wermter, S., Weber, C., Duch, W., Honkela, T., Koprinkova-Hristova, P., Magg, S., Palm, G., Villa, A.E.P. (eds.) ICANN 2014. LNCS, vol. 8681, pp. 209–216. Springer, Heidelberg (2014)CrossRefGoogle Scholar
  14. 14.
    Intel, Compute-Intensive, Highly Parallel Applications and Uses. Intel Technology Journal 09 (2005)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Bailan Feng
    • 1
  • Jinfeng Bai
    • 1
  • Zhineng Chen
    • 1
  • Xiangsheng Huang
    • 1
  • Bo Xu
    • 1
  1. 1.Interactive Digital Media Technology Research CenterInstitute of Automation, Chinese Academy of SciencesBeijingChina

Personalised recommendations