Paper-Conference

コメディドラマにおける字幕と表情を用いた笑い予測

Rethinking the evaluation of video summaries

Context-aware embeddings for automatic art analysis

情報学と物理学のクロスオーバー

Talking Head Generation with Deep Phoneme and Viseme Representation and Generative Adversarial Networks

Problems dealt with machine learning/deep learning and its applications to nuclear physics

Multimodal learning analytics: Society 5.0 project in Japan

Faces in an Archive of Buddhism Pictures

多重焦点顕微鏡画像列からの細胞の3次元形状復元

Synthesis of human shape in loose cloth using eigen-deformation