Richang Hong

About

Richang Hong is a leading researcher in affective computing, computer vision, and multimodal machine learning. His work focuses on enabling machines to perceive and understand human emotional states from video data. In his highly cited 2023 paper on the ABAW challenge, Hong developed advanced transformer-based architectures for multimodal feature extraction and fusion, achieving state-of-the-art results in both emotional reaction intensity estimation and expression classification. This work, with 19 citations, demonstrates his ability to tackle the complex, real-world challenge of affective behavior analysis in unconstrained environments. Hong has also made significant contributions to 3D pose estimation, particularly for articulated objects. His reinforcement learning approach to category-level 9D pose estimation (11 citations) addresses key challenges in shared object representation and kinematics-agnostic modeling, advancing the field of robotic manipulation and augmented reality. With a strong publication record and growing citation impact, Hong is establishing himself as a key innovator at the intersection of emotion AI and 3D scene understanding, pushing the boundaries of how machines interpret both human behavior and physical objects.

Research Focus

Key Achievements

Top Papers

1. 1
   Multimodal Feature Extraction and Fusion for Emotional Reaction Intensity Estimation and Expression Classification in Videos with Transformers

   19 citations · 2023
2. 2
   Category-Level Articulated Object 9D Pose Estimation via Reinforcement Learning

   11 citations · 2023

Key Collaborators

Contact & Links