Tsubasa Hirakawa

Unsupervised Anomaly Detection of Learning Behaviors Considering Contextual Information

Yoshihiro Yasuda, Takayoshi Yamashita, Tsubasa Hirakawa, Hironobu Fujiyoshi

With the widespread adoption of digital learning environments, learning support utilizing log data collected from Learning Management Systems (LMS) has garnered significant attention. However, many conventional learning analytics rely on aggregated metrics such as total study time or the number of accesses, …

Unsupervised Anomaly Detection of Learning Behaviors Considering Contextual Information

Yoshihiro Yasuda, Takayoshi Yamashita, Tsubasa Hirakawa, Hironobu Fujiyoshi

With the widespread adoption of digital learning environments, learning support utilizing log data collected from Learning Management Systems (LMS) has garnered significant attention. However, many conventional learning analytics rely on aggregated metrics such as total study time or the number of accesses, …

SunnyParking: Multi-Shot Trajectory Generation and Motion State Awareness for Human-like Parking

Jishu Miao, Han Chen, Jiankun Zhai, Qi Liu et autres

Autonomous parking fundamentally differs from on-road driving due to its frequent direction changes and complex maneuvering requirements. However, existing End-to-End (E2E) planning methods often simplify the parking task into a geometric path regression problem, neglecting explicit modeling of the vehicle's kinematic state. …

SunnyParking: Multi-Shot Trajectory Generation and Motion State Awareness for Human-like Parking

Jishu Miao, Han Chen, Jiankun Zhai, Qi Liu et autres

Autonomous parking fundamentally differs from on-road driving due to its frequent direction changes and complex maneuvering requirements. However, existing End-to-End (E2E) planning methods often simplify the parking task into a geometric path regression problem, neglecting explicit modeling of the vehicle's kinematic state. …

Frequency-Domain Detection of AI-Generated Images via Radial Spectrum Templates

Yuta Sato, Takayoshi Yamashita, Hironobu Fujiyoshi, Tsubasa Hirakawa

jp (code pays fourni par la source)

YUKUIv2: A Key-point Driven Diffusion Planner for Multi-shot Autonomous Parking

Jishu Miao, Han Chen, Tsubasa Hirakawa, Takayoshi Yamashita et autres

Multi-shot trajectory planning remains a critical challenge in autonomous driving and robotics, particularly when handling discontinuous motion states. To address this, we propose YUKUIv2, a novel Y-shaped trajectory planning module. Our approach introduces a key-point driven diffusion mechanism, explicitly predicting discrete transition …

jp, cn (code pays fourni par la source)

Potential of Hybrid PSF Correction to Suppress Gibbs Artifacts in PET Imaging

Tsubasa Hirakawa, Kei Wagatsuma, Muneyuki Sakata, Yuto Kamitaka et autres

Point-spread-function (PSF) correction is used to compensate for the degradation of spatial resolution in positron emission tomography (PET) imaging. PSF correction improves image contrast and reduces image noise. However, it also causes Gibbs artifacts, which appear as signal overshoot along object edges, …

jp, es (code pays fourni par la source)

Dorsoventral comparison of intraspecific variation in the butterfly wing pattern using a convolutional neural network

Kai Amino, Tsubasa Hirakawa, Masaya Yago, Takashi Matsuo

Butterfly wing patterns exhibit notable differences between the dorsal and ventral surfaces, and morphological analyses of them have provided insights into the ecological and behavioural characteristics of wing patterns. Conventional methods for dorsoventral comparisons are constrained by the need for homologous patches …

jp (code pays fourni par la source)

VLLM Guided Human-Like Guidance Navigation Generation

Masaki Nambata, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi et autres

jp (code pays fourni par la source)

2D Motion Generation Using Joint Spatial Information with 2CM-GPT

Ryota Inoue, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi

jp (code pays fourni par la source)

Visual Explanation With Action Query Transformer in Deep Reinforcement Learning and Visual Feedback via Augmented Reality

Hidenori Itaya, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi et autres

Deep Reinforcement Learning (DRL) agents possess powerful control capabilities and have potential applications in robotics and other fields. However, the closed box properties of DRL agent models still make it difficult to interpret their decision-making processes. One research area that addresses this …

jp (code pays fourni par la source)

Larval Hostplant Prediction from Luehdorfia japonica Image Using Multi-label ABN

Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi, Yuichi Oba et autres

jp (code pays fourni par la source)