2 papers
cs.CV2024
WWW: Where, Which and Whatever Enhancing Interpretability in Multimodal Deepfake Detection
Juho Jung, Sangyoun Lee, Jooeon Kang +1
All current benchmarks for multimodal deepfake detection manipulate entire frames using various generation techniques, resulting in oversaturated detection accuracies exceeding 94%…
cs.CV2024
Enhancing Temporal Action Localization: Advanced S6 Modeling with Recurrent Mechanism
Sangyoun Lee, Juho Jung, Changdae Oh +1
Temporal Action Localization (TAL) is a critical task in video analysis, identifying precise start and end times of actions. Existing methods like CNNs, RNNs, GCNs, and Transformer…