Advertisement

Online Multi-modal Person Search in Videos

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12357)

Abstract

The task of searching certain people in videos has seen increasing potential in real-world applications, such as video organization and editing. Most existing approaches are devised to work in an offline manner, where identities can only be inferred after an entire video is examined. This working manner precludes such methods from being applied to online services or those applications that require real-time responses. In this paper, we propose an online person search framework, which can recognize people in a video on the fly. This framework maintains a multi-modal memory bank at its heart as the basis for person recognition, and updates it dynamically with a policy obtained by reinforcement learning. Our experiments on a large movie dataset show that the proposed method is effective, not only achieving remarkable improvements over online schemes but also outperforming offline methods.

Keywords

Online person search Multi-modality Dynamic memory bank Uncertain instance cache Reinforcement learning 

Notes

Acknowledgment

This work is partially supported by the SenseTime Collaborative Grant on Large-scale Multi-modality Analysis (CUHK Agreement No. TS1610626 & No. TS1712093), the General Research Fund (GRF) of Hong Kong (No. 14203518 & No. 14205719), and Innovation and Technology Support Program (ITSP) Tier 2, ITS/431/18F.

References

  1. 1.
    Arandjelovic, O., Zisserman, A.: Automatic face recognition for film character retrieval in feature-length films. In: 2005 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 860–867 (2005)Google Scholar
  2. 2.
    Chung, J.S.: Naver at ActivityNet challenge 2019-task B active speaker detection (AVA). arXiv preprint arXiv:1906.10555 (2019)
  3. 3.
    Cour, T., Sapp, B., Nagle, A., Taskar, B.: Talking pictures: temporal grouping and dialog-supervised person recognition. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1014–1021 (2010)Google Scholar
  4. 4.
    Erzin, E., Yemez, Y., Tekalp, A.M.: Multimodal speaker identification using an adaptive classifier cascade based on modality reliability. IEEE Trans. Multimedia 7(5), 840–852 (2005)CrossRefGoogle Scholar
  5. 5.
    Everingham, M., Sivic, J., Zisserman, A.: “Hello! my name is... Buffy”-automatic naming of characters in TV video. In: 2006 British Machine Vision Conference (BMVC), pp. 899–908 (2006)Google Scholar
  6. 6.
    Farenzena, M., Bazzani, L., Perina, A., Murino, V., Cristani, M.: Person re-identification by symmetry-driven accumulation of local features. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2360–2367 (2010)Google Scholar
  7. 7.
    Feng, L., Li, Z., Kuang, Z., Zhang, W.: Extractive video summarizer with memory augmented neural networks. In: 2018 ACM International Conference on Multimedia (MM), pp. 976–983 (2018)Google Scholar
  8. 8.
    Gheissari, N., Sebastian, T.B., Hartley, R.: Person reidentification using spatiotemporal appearance. In: 2006 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1528–1535 (2006)Google Scholar
  9. 9.
    Graves, A., Wayne, G., Danihelka, I.: Neural turing machines. arXiv preprint arXiv:1410.5401 (2014)
  10. 10.
    Guo, Y., Zhang, L., Hu, Y., He, X., Gao, J.: MS-Celeb-1M: a dataset and benchmark for large-scale face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 87–102. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46487-9_6CrossRefGoogle Scholar
  11. 11.
    Haurilet, M., Tapaswi, M., Al-Halah, Z., Stiefelhagen, R.: Naming TV characters by watching and analyzing dialogs. In: 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1–9 (2016)Google Scholar
  12. 12.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)Google Scholar
  13. 13.
    Hu, D., Li, X., Lu, X.: Temporal multimodal learning in audiovisual speech recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3574–3582 (2016)Google Scholar
  14. 14.
    Hu, Y., Ren, J.S., Dai, J., Yuan, C., Xu, L., Wang, W.: Deep multimodal speaker naming. In: 2015 ACM International Conference on Multimedia (MM), pp. 1107–1110 (2015)Google Scholar
  15. 15.
    Huang, Q., Xiong, Y., Lin, D.: Unifying identification and context learning for person recognition. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2217–2225 (2018)Google Scholar
  16. 16.
    Huang, Q., Liu, W., Lin, D.: Person search in videos with one portrait through visual and temporal links. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 437–454. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01261-8_26CrossRefGoogle Scholar
  17. 17.
    Huang, Q., Xiong, Y., Rao, A., Wang, J., Lin, D.: MovieNet: a holistic dataset for movie understanding. In: 2020 European Conference on Computer Vision (ECCV) (2020)Google Scholar
  18. 18.
    Li, D., Kadav, A.: Adaptive memory networks. In: 2018 International Conference on Learning Representations Workshop (ICLRW) (2018)Google Scholar
  19. 19.
    Lin, D., Kapoor, A., Hua, G., Baker, S.: Joint people, event, and location recognition in personal photo collections using cross-domain context. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6311, pp. 243–256. Springer, Heidelberg (2010).  https://doi.org/10.1007/978-3-642-15549-9_18CrossRefGoogle Scholar
  20. 20.
    Liu, Z., Wang, J., Gong, S., Lu, H., Tao, D.: Deep reinforcement active learning for human-in-the-loop person re-identification. In: 2019 IEEE International Conference on Computer Vision (ICCV), pp. 6121–6130 (2019)Google Scholar
  21. 21.
    Logan, B.: Mel frequency cepstral coefficients for music modeling. In: 2000 International Symposium on Music Information Retrieval (ISMIR) (2000)Google Scholar
  22. 22.
    Loy, C.C., et al.: Wider face and pedestrian challenge 2018: methods and results. arXiv preprint arXiv:1902.06854 (2019)
  23. 23.
    Maaten, L.V.D., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(Nov), 2579–2605 (2008)zbMATHGoogle Scholar
  24. 24.
    Na, S., Lee, S., Kim, J., Kim, G.: A read-write memory network for movie story understanding. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 677–685 (2017)Google Scholar
  25. 25.
    Nagrani, A., Zisserman, A.: From Benedict Cumberbatch to Sherlock Holmes: character identification in TV series without a script. In: 2017 British Machine Vision Conference (BMVC), pp. 107.1–107.13 (2017)Google Scholar
  26. 26.
    Ouyang, D., Shao, J., Zhang, Y., Yang, Y., Shen, H.T.: Video-based person re-identification via self-paced learning and deep reinforcement learning framework. In: 2018 ACM International Conference on Multimedia (MM), pp. 1562–1570 (2018)Google Scholar
  27. 27.
    Rao, A., et al.: A unified framework for shot type classification based on subject centric lens. In: 2020 European Conference on Computer Vision (ECCV) (2020)Google Scholar
  28. 28.
    Rao, A., et al.: A local-to-global approach to multi-modal movie scene segmentation. In: 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10146–10155 (2020)Google Scholar
  29. 29.
    Rao, Y., Lu, J., Zhou, J.: Attention-aware deep reinforcement learning for video face recognition. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 3951–3960 (2017)Google Scholar
  30. 30.
    Ren, J.S.J., et al.: Look, listen and learn - a multimodal LSTM for speaker identification. In: 2016 AAAI Conference on Artificial Intelligence (AAAI), pp. 3581–3587 (2016)Google Scholar
  31. 31.
    Roth, J., et al.: AVA-active speaker: an audio-visual dataset for active speaker detection. arXiv preprint arXiv:1901.01342 (2019)
  32. 32.
    Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015)MathSciNetCrossRefGoogle Scholar
  33. 33.
    Shen, Y., Tan, S., Hosseini, A., Lin, Z., Sordoni, A., Courville, A.C.: Ordered memory. In: Advances in Neural Information Processing Systems, pp. 5037–5048 (2019)Google Scholar
  34. 34.
    Sivic, J., Everingham, M., Zisserman, A.: “Who are you?” - learning person specific classifiers from video. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1145–1152 (2009)Google Scholar
  35. 35.
    Sukhbaatar, S., Szlam, A., Weston, J., Fergus, R.: End-to-end memory networks. In: Advances in Neural Information Processing Systems, pp. 2440–2448 (2015)Google Scholar
  36. 36.
    Sutton, R.S., Barto, A.G.: Reinforcement learning: an introduction. IEEE Trans. Neural Netw. 9(5), 1054–1054 (1998)CrossRefGoogle Scholar
  37. 37.
    Wang, J., Wang, W., Huang, Y., Wang, L., Tan, T.: Hierarchical memory modelling for video captioning. In: 2018 ACM International Conference on Multimedia (MM), pp. 63–71 (2018)Google Scholar
  38. 38.
    Wang, J., Wang, W., Wang, Z., Wang, L., Feng, D., Tan, T.: Stacked memory network for video summarization. In: 2019 ACM International Conference on Multimedia (MM), pp. 836–844 (2019)Google Scholar
  39. 39.
    Weston, J., Chopra, S., Bordes, A.: Memory networks. In: 2015 International Conference on Learning Representations (ICLR) (2015)Google Scholar
  40. 40.
    Yang, T., Chan, A.B.: Learning dynamic memory networks for object tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 153–169. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01240-3_10CrossRefGoogle Scholar
  41. 41.
    Zajdel, W., Zivkovic, Z., Krose, B.J.A.: Keeping track of humans: have I seen this person before? In: 2005 IEEE International Conference on Robotics and Automation (ICRA), pp. 2081–2086 (2005)Google Scholar
  42. 42.
    Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process. Lett. 23(10), 1499–1503 (2016)CrossRefGoogle Scholar
  43. 43.
    Zhang, N., Paluri, M., Taigman, Y., Fergus, R., Bourdev, L.: Beyond frontal faces: improving person recognition using multiple cues. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4804–4813 (2015)Google Scholar
  44. 44.
    Zhang, W., He, X., Lu, W., Qiao, H., Li, Y.: Feature aggregation with reinforcement learning for video-based person re-identification. IEEE Trans. Neural Netw. Learn. Syst. 30(12), 3847–3852 (2019)CrossRefGoogle Scholar
  45. 45.
    Zheng, L., et al.: MARS: a video benchmark for large-scale person re-identification. In: 2016 European Conference on Computer Vision (ECCV), pp. 868–884 (2016)Google Scholar
  46. 46.
    Zhou, D., Bousquet, O., Lal, T.N., Weston, J., Schölkopf, B.: Learning with local and global consistency. In: Advances in Neural Information Processing Systems, pp. 321–328 (2003)Google Scholar
  47. 47.
    Zhou, H., Liu, Z., Xu, X., Luo, P., Wang, X.: Vision-infused deep audio inpainting. In: 2019 IEEE International Conference on Computer Vision (ICCV), pp. 283–292 (2019)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Department of Computer Science and TechnologyTsinghua UniversityBeijingChina
  2. 2.CUHK-SenseTime Joint LabThe Chinese University of Hong KongHong KongChina

Personalised recommendations