高部雅矢/Masaya Takabe: 意味情報を考慮した3D ガウシアンスプラッティング (3D Gaussian Splatting with Semantic information)
巽 優衣/Yui Tatsumi: 明示的な残差情報を用いた視聴と画像認識のための階層画像符号化 (Scalable Image Coding for Humans and Machines Using Explicit Residual Information)
田中頌子/Shoko Tanaka: 暗黙的ニューラル表現に基づく画像符号化のためのコンテキストモデルの作成 (Context Modeling for Image Coding Based on Implicit Neural Representations)
蒐場涼介/Ryosuke Nutaba: モデルパラメータの信頼度を考慮した層ごとのFederated Learning (Layer-wise Federated Learning Considering Model Parameter Reliability)
李 沃桐/Wotong Li: SuperGlue-Based Deep Learning Method for Image Matching from Multiple Viewpoints
陳高思衛/Gaosiheng Chen:
殷墨涵/Mohan Yin: Traffic Sign Detection n Complex Scenarios Based on Collaborative Perception of NeRF and LiDAR (tantative)
景奕驊/Yihua Jing: Improving Audio-Video Speech Recognition Performance through Multimodal Data Enhancement: Exploration of Using Video Data to Support Lmited Audio Datasets (tentative)
謝維靖/Weijing Xie: Integrating SAM-Med2D and NeRF for Advanced 3D Brain Tumor Segmentation in Medical Imaging (tantative)
陈梓萌/Zimeng Chen: FusionX: Empower Large Multimodal Models by Unified Processing and Reinforcement Learning (tantative)