Semi-Supervised Feature Embedding for Data Sanitization in Real-World Events

• Published in: Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 2495 - 2499
• Main Authors: Lavi, Bahram, Nascimento, Jose, Rocha, Anderson
• Format: Conference Proceeding
• Language: English
• Published: IEEE 06.06.2021
• Subjects: Conferences; data relevance analysis; feature embedding; forensic application; Image sanitization; semi-supervised learning; Semisupervised learning; Signal processing; Signal processing algorithms; Social networking (online); Supervised learning; Training
• ISSN: 2379-190X
• DOI: 10.1109/ICASSP39728.2021.9414461

With the rapid growth of data sharing through social media networks, determining relevant data items concerning a particular subject becomes paramount. We address the issue of establishing which images represent an event of interest through a semi-supervised learning technique. The method learns consistent and shared features related to an event (from a small set of examples) to propagate them to an unlabeled set. We investigate the behavior of five image feature representations considering low- and high-level features and their combinations. We evaluate the effectiveness of the feature embedding approach on five collected datasets from real-world events.