Kibum Kim
Papers
9
Total Citations
754
H-Index
9
About
Kibum Kim is a prolific researcher specializing in computer vision, human activity recognition, and intelligent sensing systems, with a particular focus on bridging machine learning with real-world healthcare and environmental applications. His work has garnered significant academic attention, accumulating over 750 citations across his most influential publications. Kim's most celebrated contribution — his 2021 study on automatic human posture estimation for sport activity recognition using entropy Markov models (161 citations) — exemplifies his talent for combining probabilistic modeling with robust body-part detection. Complementing this, his wearable inertial sensor research applies Adam optimization and Maximum Entropy Markov Models to daily activity analysis, directly addressing elderly healthcare and independent living challenges. Beyond human motion, Kim has made substantial strides in scene classification and multi-object segmentation, developing statistical and depth-image-based frameworks that push the boundaries of indoor-outdoor environment understanding. His work on sustainable object recognition using kernel sliding perceptron and modified sampling consensus further demonstrates his commitment to practical, scalable solutions in robotics and surveillance. More recently, Kim has expanded into facial expression recognition and age estimation using deep learning, signaling a broadening research vision. For students exploring computer vision or smart healthcare systems, Kim's body of work offers a rigorous yet applied foundation worth deep engagement.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9