Tomoyuki Suzuki is an Applied Research Scientist at CyberAgent.
His current research interest is computer vision for creative work, including video/image decomposition, representation learning, and agentic systems for content creation and editing.
He received his Ph.D. in March 2025 under the supervision of Prof. Yoshimitsu Aoki working on video recognition.
Previously, he was a research engineer at DeNA, working on CV/ML R&D in the mobility domain. He also worked as a part-time researcher at AIST, conducting research on video event anticipation and visual representation learning.
For more details, please refer to his CV.
Tomoyuki Suzuki, Kang-Jun Liu, Naoto Inoue, Kota Yamaguchi, “LayerD: Decomposing Raster Graphic Designs into Layers”, ICCV 2025. (acceptance rate 24%) [Paper] [Project]
Takahiro Shirakawa, Tomoyuki Suzuki, Daichi Haraguchi, “MG-Gen: Single Image to Motion Graphics Generation”, ICCV Workshops 2025. [Paper] [Project]
Tomoyuki Suzuki, Kotaro Kikuchi, Kota Yamaguchi, “Fast Sprite Decomposition from Animated Graphics”, ECCV 2024. (acceptance rate 27.9%) [Paper] [Project]
Shoko Sawada, Tomoyuki Suzuki, Kota Yamaguchi, Masashi Toyoda, “Visual Explanation for Advertising Creative Workflow”, CHI EA 2024. (acceptance rate 33.9%) [Paper]
Tomoyuki Suzuki*, Hirokatsu Kataoka*, Yoshimitsu Aoki, Yutaka Satoh, “Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB”, CVPR 2018. (acceptance rate 29.6%) [Paper] [Poster]
Tomoyuki Suzuki, Takahiro Itazuri, Kensho Hara, Hirokatsu Kataoka, “Learning Spatiotemporal 3D Convolution with Video Order Self-Supervision”, ECCV Workshops 2018. [Paper]
Tomoyuki Suzuki, Munetaka Minoguchi, Ryota Suzuki, Akio Nakamura, Kenji Iwata, Yutaka Satoh, Hirokatsu Kataoka, “Semantic Change Detection”, ICARCV, 2018.
Kaori Abe, Munetaka Minoguchi, Teppei Suzuki, Tomoyuki Suzuki, Naofumi Akimoto, Yue Qiu, Ryota Suzuki, Kenji Iwata, Yutaka Satoh, Hirokatsu Kataoka, “Fashion Culture Database: Construction of Database for World-wide Fashion Analysis”, ICARCV 2018.
Tomoyuki Suzuki, Yoshimitsu Aoki, “RetinaViT: Efficient Visual Backbone for Online Video Streams”, Sensors, 24 (17), 2024. [Link]
Tomoyuki Suzuki, Yoshimitsu Aoki, “Efficient Transformer-Based Compressed Video Modeling via Informative Patch Selection”, Sensors, 23 (1), 2022. [Link]
Tomoyuki Suzuki, Yoshimitsu Aoki, “Time-sequential action recognition using pose-centric learning for action-transition videos”, Journal of the Japan Society for Precision Engineering, 83 (12), 2017. [Link]
id: tomoyukun