Publications

Yuga Yano, Daiju Kanaoka, Hakaru Tamukoh, Yasutomo Kawanishi, "SaaF: Scene-Specific Ambiguity-Aware 3D Language Fields towards Interactive Real-World Object Retrieval", The 2026 IEEE/RSJ International Conference on Robots and Systems (IROS), 2026.

Tomohiro Fujita, Yasutomo Kawanishi, "Lightweight Gating Mechanism for RNNs with Sech-Based Vector Gates", The 28th International Conference on Pattern Recognition (ICPR), 2026.

Trung Thanh Nguyen, Daniel Lusk, Kilian Gerberding, Janusch Vajna-Jehle, Tuan-Anh Vu, Duc Viet Le, Tu Vo, Phi Le Nguyen, Yasutomo Kawanishi, Takahiro Komamizu, Ichiro Ide, Julian Frey, Teja Kattenborn, "SelectAnyTree: A Promptable Instance Segmentation Model for 3D Forest LiDAR Point Clouds", arXiv preprint arXiv:2606.27491, 2026.

Vijay John, Yasutomo Kawanishi, "Frame-Level Driver Drowsiness Detection with Deep Embedded Clustering-based Pseudo Label Refinement", The 2026 IEEE Intelligent Vehicles Symposium (IV), WePo3-1.8, 2026.

Duc Tri Tran, Trung Thanh Nguyen, Vijay John, Phi Le Nguyen, Yasutomo Kawanishi, "TraRA: Trajectory-level Recognition Aggregation for Video Text Spotting in Urban Surveillance", arXiv preprint arXiv:2606.07161, 2026.

Trung Thanh Nguyen, Tuan-Anh Vu, Duc Viet Le, Yasutomo Kawanishi, Takahiro Komamizu, Ichiro Ide, Teja Kattenborn, "ForestMamba: Sparse Mamba with Geometry-guided Queries for 3D Forest Point Cloud Segmentation", arXiv preprint arXiv:2606.01549, 2026.

Shu Nakamura, Ryo Kawahara, Genki Kinoshita, Ryosuke Hirai, Yasutomo Kawanishi, Shohei Nobuhara, Ko Nishino, "REACH: Hand Pose Estimation from Room Corners", arXiv preprint arXiv:2605.22231, 2026.

Motoharu Sonogashira, Masaaki Iiyama, Yasutomo Kawanishi, "Self-Supervised Learning for Open-Set Scene Graph Generation by Unknown-Object and Relationship Pseudo-Labels", IEEE Access, 2026.

Genki Kinoshita, Shu Nakamura, Ryo Kawahara, Shohei Nobuhara, Yasutomo Kawanishi, Ko Nishino, "Action Motifs: Self-Supervised Hierarchical Representation of Human Body Movements", arXiv preprint arXiv:2604.28173, 2026.

Trung Thanh Nguyen, Vijay John, Yasutomo Kawanishi, Takahiro Komamizu, Ichiro Ide, "MultiSensor-Home: Multi-modal Multi-view Dataset and Benchmarks for Action Recognition in Home Environments", Pattern Recognition, vol. 179, part C, November 2026, 113810..

Vijay John, Yasutomo Kawanishi, "Hierarchical graph attention networks with spatio-temporal class tokens for distributed audio-visual event classification", Multimed Tools Appl vol. 85, no. 343, April 2026.