Interaktivní vyhledávání v rozsáhlých kolekcích videa
Thesis title in Czech: | Interaktivní vyhledávání v rozsáhlých kolekcích videa |
---|---|
Thesis title in English: | Interactive retrieval in large video collections |
Key words: | Interaktivní hledání ve videu, hluboké učení, podobnostní hledání, hledání známé scény |
English key words: | Interactive video retrieval, deep learning, similarity search, known-item search |
Academic year of topic announcement: | 2022/2023 |
Thesis type: | dissertation |
Thesis language: | |
Department: | Department of Software Engineering (32-KSI) |
Supervisor: | doc. RNDr. Jakub Lokoč, Ph.D. |
Author: |
Guidelines |
Video retrieval still represents a challenging problem for multimedia management systems. Especially tasks like known-item or ad-hoc search focusing on high recall require both effective retrieval models and interactive interfaces. The objective of this work is to design new models and methods improving effectiveness of interactive video retrieval processes in large collections. The methods will be compared with related systems at international evaluation campaigns (e.g., Video Browser Showdown or Lifelog Search Challenge). |
References |
B. Zoph, V. Vasudevan, J. Shlens, and Q. V. Le. Learning transferable architectures for scalable image recognition. CoRR, abs/1707.07012, 2017.
O. Vinyals, A. Toshev, S. Bengio, and D. Erhan. Show and tell: Lessons learned from the 2015 MSCOCO image captioning challenge. IEEE Trans. Pattern Anal. Mach. Intell., 39(4):652–663, 2017. K. Schoeffmann, M. A. Hudelist, and J. Huber. Video interaction tools: A survey of recent work. ACM Comput. Surv., 48(1):14:1–14:34, Sept. 2015. J. Lokoc, W. Bailer, K. Schoeffmann, B. Muenzer, and G. Awad. On influential trends in interactive video retrieval: Video browser showdown 2015-2017. IEEE Trans. Multimedia, 20(12):3361–3376, 2018 |