2 code implementations • 22 Apr 2017 • Sungeun Hong, Woobin Im, Hyun S. Yang
Up to now, only limited research has been conducted on cross-modal retrieval of suitable music for a specified video or vice versa.
no code implementations • 15 Feb 2017 • Sungeun Hong, Jongbin Ryu, Woobin Im, Hyun S. Yang
A fully connected layer is used to select the key frames and key segments, while the convolutional layer is used to describe them.
1 code implementation • 14 Feb 2017 • Sungeun Hong, Woobin Im, Jongbin Ryu, Hyun S. Yang
In the proposed approach, domain adaptation, feature extraction, and classification are performed jointly using a deep architecture with domain-adversarial training.