小泉翔/Kakeru Koizumi: メトリック深度推定に基づく単眼SLAMの安定化に関する研究 (Stabilizing Monocular SLAM via Metric Depth Estimation)
細郷壮希/Souki Saigo: 文脈に基づくフレーム選択による動画内人物に焦点を当てた連続感情認識 (Continuous Emotion Recognition via Frame Selection Based on Contextual Information Focusing on Characters in Video)
速見泰雅/Taiga Hayami : 暗黙的ニューラル表現における効率的な動画埋込 (Efficient Video Embedding in Implicit Neural Representation)
范洪睿/Hongrui Fan: 特徴強化手法を用いた物体検出モデルの検出精度向上に関する研究 (Research on Detection Accuracy Improvement of Object Detection Models Using Feature Enhancement Methods)
Taira Kunitomi/國富平: Clinically Prioritized Fusion Incorporating Slice-Level Attention and Continuity Modeling for Robust Knee MRI injury Classification
Bingyu Lu/卢冰或: Multimodal Object Detection
Ziyue Zeng/曾子越: Advances of Diffusion Models and Their Applications in Image and Video Generation