K
Kuan-Ting Lai
Researcher at National Taipei University of Technology
Publications - 24
Citations - 446
Kuan-Ting Lai is an academic researcher from National Taipei University of Technology. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 8, co-authored 18 publications receiving 363 citations. Previous affiliations of Kuan-Ting Lai include Center for Information Technology & National Taiwan University.
Papers
More filters
Proceedings ArticleDOI
Video Event Detection by Inferring Temporal Instance Labels
TL;DR: A large-margin formulation which treats the instance labels as hidden latent variables, and simultaneously infers the instancelabel as well as the instance-level classification model, which infers optimal solutions that assume positive videos have a large number of positive instances while negative videos have the fewest ones.
Proceedings ArticleDOI
Sample-Specific Late Fusion for Visual Category Recognition
TL;DR: This paper identifies the optimal fusion weights for each sample and pushes positive samples to top positions in the fusion score rank list, and forms the problem as a L∞ norm constrained optimization problem and applies the Alternating Direction Method of Multipliers for the optimization.
Proceedings ArticleDOI
Human Action Recognition Using Histogram of Oriented Gradient of Motion History Image
TL;DR: The proposed human action recognition method using histogram of oriented gradient (HOG) of motion history image (MHI) does not require the generation process of human silhouette, and therefore the performance is increased.
Book ChapterDOI
Recognizing Complex Events in Videos by Learning Key Static-Dynamic Evidences
TL;DR: Experiments on large-scale video datasets show that the proposed novel method can improve the detection accuracy while providing the unique capability in discovering key evidences of each complex event.
Journal ArticleDOI
Learning Sample Specific Weights for Late Fusion
TL;DR: This paper casts late fusion into an information propagation process that diffuses the fusion weights of labeled samples to the individual unlabeled samples, and enforce positive samples to have higher fusion scores than negative samples to achieve better accuracy.