NEWS お知らせ

世界最高峰の信号処理に関する国際会議 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2024)にメディアダイナミクス研究室より投稿した以下の9件の論文が採択されました！
ICASSPは、IEEE Signal Processing Societyのフラグシップカンファレンスであり、Google ScholarのSignal Processingのカテゴリにおける国際会議の中で1位にランクしています。来年は韓国ソウルで開催です。
【Regular Track】
[1] Masaki Kashiwagi, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Enhancing Noisy Label Learning via Unsupervised Contrastive Loss with Label Correction Based on Prior Knowledge”
[2] Masaya Sato, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Caption Unification for Multi-view Lifelogging Images Based on In-context Learning with Heterogeneous Semantic Contents”
[3] Haruka Matsuda, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Multi-object Editting in Personalized Text-to-image Diffusion Models via Segmentation Guidance”
[4] Tatsuki Seino, Naoki Saito, Takahiro Ogawa, Satoshi Asamizu, Miki Haseyama, “Confidence-aware Spatial-temporal Attention Graph Convolutoinal Network for Skeleton-based Expert-Novice Level Classification”
[5] Yuhu Feng, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Privacy Preserving Gaze Estimation via Federated Learning Adapted to Egocentric Video”
[6] He Zhu, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Prompt-based Personalized Federated Learning for Medical Visual Question Answering”
【OJSP Track】
[7] Zongyao Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Source-data-free cross-domain knowledge transfer for semantic segmentation”
[8] Yuya Moroto, Yingrui Ye, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Zero-shot Visual Sentiment Prediction via Cross-domain Knowledge Distillation”
[9] Yuto Watanabe, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “TolerantGAN: Text-guided Image Manipulation Tolerant to Real-world Image”