Congratulations to the student team composed of Phan Nguyen Huu Phong, Tran Duc Luong, Le Hoang Phuc, Tran Dinh Khoa, and Tran Kim Ngoc Ngan from TeamQ - Wanna.W1n Information Security Club, and the research group InSecLab, for having their research paper on Lifelog Event Retrieval (Event Retrieval in Videos) accepted for presentation at the 12th Symposium on Information and Communication Technology (SoICT 2023) - an international scientific conference.
The scientific paper is the result of the research and development process aiming to efficiently query everyday life event information from video data in the AI Challenge 2023. This achievement is an encouraging milestone for TeamQ members who conducted scientific research and participated in academic competitions related to the applications of Artificial Intelligence (AI) in various aspects of life within the Information Security Lab (InSecLab) through the WannaQuest Q2023.1 training program.
Details of the Scientific Paper:
Paper Title: "DoppelSearch: A Novel Approach to Content-Based Video Retrieval for AI Challenge HCMC 2023"
Student Contributors:
Phan Nguyen Huu Phong - Computer Science Talent Program (KHTN2022)
Tran Duc Luong - Information Security Talent Program (ATTN2019)
Le Hoang Phuc - High-Quality Information Technology Program (CNCL2020)
Tran Dinh Khoa - Information Security Talent Program (ATTN2022)
Tran Kim Ngoc Ngan - Computer Science Talent Program (KHTN2022)
Supervisors: Dr. Pham Van Hau & B.S. Nguyen Huu Quyen
General Information about the Conference:
SoICT 2023 is an international scientific conference focusing on information technology and communication. It covers essential research areas, including AI and Big Data foundations, Networking Technologies and Communications, Image Processing and Natural Language, Software Engineering, Artificial Intelligence, Digital Technologies, Information Security, and Event Retrieval from Videos.
SoICT 2023 will be held in Ho Chi Minh City and organized by the School of Information and Communication Technology - Hanoi University of Science and Technology, VNUHCM-University of Science, Laboratory Informatics, Modelling, and Optimization System (LIMOS), The French National Centre for Scientific Research (CNRS), and the Institute of Advanced Studies in Mathematics on December 7-8, 2023.
Abstract: "Video retrieval, which has been considered as a critical task in the field of computer vision and pattern recognition recently, finds extensive applications in several aspects such as education, entertainment, security, and healthcare. However, it faces challenges due to the complexity of video data, the instability in feature extraction methods, or the semantic disparities between videos and text. In this paper, we present a novel approach for content-based video retrieval, named DoppelSearch, leveraging the CLIP (Contrastive Language-Image Pre-training) model architecture to classify and label video segments, offering users the ability to search for videos based on specific content . Our method capitalizes on the ViT-b/32 model for feature extraction and employs feature embedding, in conjunction with the Faiss library, to enhance search efficiency. Experimental results demonstrate our model's high accuracy and swift retrieval times, promising new opportunities in content-based video retrieval for researchers, developers, and end-users. This paper not only introduces the application of the CLIP and ViT-b/32 models, but also elaborates on the specific feature extraction process and the utilization of Faiss for optimizing video retrieval. The DoppelSearch method represents a significant stride in the field of video retrieval and holds promise for diverse applications across various industries."
Link to the conference: https://soict.org/submission/paper-submission/
For more details, visit: https://www.facebook.com/inseclab/posts/pfbid0urDxEpRAJGgYRgRbfFv...
Ha Bang - Media Collaborator, University of Information Technology
Translation: Nhat Hien