Vijay John

RIKEN — Japan

Computer Science · Physical Sciences

21h-index1.6kcitations84works0.82yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Video Surveillance and Tracking Methods(30), Advanced Vision and Imaging(18), Advanced Neural Network Applications(17), Human Pose and Action Recognition(17), Autonomous Vehicle Technology and Safety(13)

Publications84 total

Bidirectional Translation System for Tamil Sign Language Recognition
Lecture notes in networks and systems·2026
Next‐Generation Industrial Robots
2025
Surgical Robots in Urology and Gynecology
2025
View-aware Cross-modal Distillation for Multi-view Action Recognition
arXiv (Cornell University)·2025Open Access
Reproducibility Companion Paper: Enhancing Model Interpretability with Local Attribution over Global Exploration
2025Open Access
SemGest: A Multimodal Feature Space Alignment and Fusion Framework for Semantic-aware Co-speech Gesture Generation
2025Open Access
Modelling Spatio-Temporal Dynamics by Graph Attention Network for Distributed Multi-Microphone Sound Event Classification
2025
Action Selection Learning for Weakly Labeled Multi-modal Multi-view Action Recognition
ACM Transactions on Multimedia Computing Communications and Applications·2025· 1 cited
Trending technologies and application of generative AI
2025· 1 cited
Cross-modal Emotion-specific Attention model for Multimodal Emotion Recognition
2025· 1 cited
MultiSensor-Home: A Wide-area Multi-modal Multi-view Dataset for Action Recognition and Transformer-based Sensor Fusion
2025· 1 cited
Intelligent Psyllid Monitoring Based on DiTs-YOLOv10-SOD
IEEE Transactions on AgriFood Electronics·2025· 1 cited
Multimodal Cascaded Framework with Multimodal Latent Loss Functions Robust to Missing Modalities
ACM Transactions on Multimedia Computing Communications and Applications·2025· 1 cited
Generating Pseudo-Strong Labels from Weak Labels for Distributed Multi-Microphone Sound Event Detection
Lecture notes in computer science·2024· 1 cited
Frame-Level Latent Embedding Using Weak Labels for Multi-View Action Recognition
2024· 1 cited
Multi-View Video-Based Learning: Leveraging Weak Labels for Frame-Level Perception
arXiv (Cornell University)·2024Open Access
Polylanenet++: enhancing the polynomial regression lane detection based on spatio-temporal fusion
Signal Image and Video Processing·2024· 5 cited
Action Selection Learning for Weakly Labeled Multi-Modal Multi-View Action Recognition
SSRN Electronic Journal·2024· 1 citedOpen Access
Combining Knowledge Distillation and Transfer Learning for Sensor Fusion in Visible and Thermal Camera-based Person Classification
2023
Multimodal Cascaded Framework with Metric Learning Robust to Missing Modalities for Person Classification
2023· 4 citedOpen Access
page 1 of 5Next →

Frequent Co-authors

Seiichi Mita(23), Zheng Liu(15), Ali Boyali(8), S. Mita(7), Hossein Tehrani(6), Bin Qi(5), Emanuele Trucco(5), Erik Blasch(5), Kiyosumi Kidono(4), Kazuhisa Ishimaru(4), Chunzhao Guo(3), Špela Ivekovič(3), Yuquan Xu(3), Shuo Liu(3), M. K. Nithilan(3), Gwenn Englebienne(3), Ben Kröse(3), Long Qian(3), Zheng Liu(2), Masayuki Imanishi(2)