Kensho Hara

5 papers · 2018–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11) ❓ The Questioner

Venues

WACV (2) CVPR (1) ECCV (1) ICCV (1)

Top co-authors

Hirokatsu Kataoka (4) Yutaka Satoh (3) Yue Qiu (2) Nakamasa Inoue (2) Kenji Iwata (1) Yanjun Sun (1) Eisuke Yamagata (1) Rio Yokota (1) Ken Fukuda (1) Ryusuke Sagawa (1)

Research topics

Computer Vision (3) Deep Learning (2) Machine Learning (2) Analysis (2) Architectures (2) Artificial Intelligence (1) Application Areas (1) Core AI (1) Learning Types (1) Processing (1) Techniques (1)

Keywords

video classification (2) action recognition (2) video recognition (1) data augmentation (1) multimodal learning (1) video understanding (1) human-object interaction (1) scene graph generation (1) instruction tuning (1) fine-grained recognition (1) convolutional neural network (1) residual network (1) spatio-temporal feature (1) 3d convolutional neural network (1) motion pattern (1) video large language model (1) multi-video reasoning (1) fine-grained video understanding (1) video instruction tuning (1) large language model (1)

Papers

VideoSetDiff: Identifying and Reasoning Similarities and Differences in Similar Videos ICCV 2025 Formula-Supervised Visual-Geometric Pre-training ECCV 2024 VirtualHome Action Genome: A Simulated Spatio-Temporal Scene Graph Dataset With Consistent Relationship Labels WACV 2023 Spatiotemporal Initialization for 3D CNNs With Generated Motion Patterns WACV 2022 Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet? CVPR 2018