Abstract
This paper introduces our multimedia retrieval system for the Video Browser Showdown 2022 competition. The system was built for interactive retrieval task in a large video collection by focusing on four fundamental methods. First, we allow users to search by object features such as position and color. Secondly, our system also supports searching by text instances appearing in video segments. Next, we support searching by visual-textual association. And finally, the system can also search for videos containing a specific audio category. Moreover, we extend our framework to support temporal queries for all of the mentioned features.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Berns, F., et al.: V3C1 dataset: an evaluation of content characteristics. In: Proceedings of the 2019 on International Conference on Multimedia Retrieval, pp. 334–338 (2019)
Du, Y., et al.: PP-OCR: a practical ultra lightweight OCR system. arXiv preprint arXiv:2009.09941 (2020)
Gemmeke, J.F., et al.: Audio set: an ontology and human-labeled dataset for audio events. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 776–780. IEEE (2017)
Heller, S., et al.: Towards explainable interactive multi-modal video retrieval with Vitrivr. In: Lokoč, J., et al. (eds.) MMM 2021. LNCS, vol. 12573, pp. 435–440. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-67835-7_41
Johnson, J., Douze, M., Jégou, H.: Billion-scale similarity search with GPUs. arXiv preprint arXiv:1702.08734 (2017)
Kong, Q., et al.: PANNs: large-scale pretrained audio neural networks for audio pattern recognition. IEEE/ACM Trans. Audio Speech Lang. Process. 28, 2880–2894 (2020)
Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123(1), 32–73 (2017)
Le, N.-K., Nguyen, D.-H., Tran, M.-T.: An interactive video search platform for multi-modal retrieval with advanced concepts. In: Ro, Y.M., et al. (eds.) MMM 2020. LNCS, vol. 11962, pp. 766–771. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-37734-2_67
Lokoč, J., Kovalčík, G., Souček, T.: VIRET at video browser showdown 2020. In: Ro, Y.M., et al. (eds.) MMM 2020. LNCS, vol. 11962, pp. 784–789. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-37734-2_70
Radford, A., et al.: Learning transferable visual models from natural language supervision. arXiv preprint arXiv:2103.00020 (2021)
Ren, S., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural. Inf. Process. Syst. 28, 91–99 (2015)
Ressmann, A., Schoeffmann, K.: IVOS - the ITEC interactive video object search system at VBS2021. In: Lokoč, J., et al. (eds.) MMM 2021. LNCS, vol. 12573, pp. 479–483. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-67835-7_48
Rossetto, L., Schoeffmann, K., Bernstein, A.: Insights on the V3C2 dataset. arXiv preprint arXiv:2105.01475 (2021)
Rossetto, L., et al.: Interactive video retrieval in the age of deep learning. Detailed evaluation of VBS 2019. IEEE Trans. Multimedia 23, 243–256 (2020)
Rossetto, L., et al.: On the user-centric comparative remote evaluation of interactive video search systems. IEEE MultiMedia 28(4), 18–28 (2021)
Soucek, T., Lokoc, J.: TransNet V2: an effective deep network architecture for fast shot transition detection. CoRR abs/2008.04838, arXiv: 2008.04838 (2020)
Acknowledgement
This research is funded by University of Information Technology - Vietnam National University Ho Chi Minh City under grant number D1-2022-01.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Ho, K. et al. (2022). UIT at VBS 2022: An Unified and Interactive Video Retrieval System with Temporal Search. In: Þór Jónsson, B., et al. MultiMedia Modeling. MMM 2022. Lecture Notes in Computer Science, vol 13142. Springer, Cham. https://doi.org/10.1007/978-3-030-98355-0_54
Download citation
DOI: https://doi.org/10.1007/978-3-030-98355-0_54
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-98354-3
Online ISBN: 978-3-030-98355-0
eBook Packages: Computer ScienceComputer Science (R0)