10 Papers
16 Citations
Kai Chen is an academic researcher from National University of Defense Technology. The author has contributed to research in topics: Facial recognition system & Graph (abstract data type). The author has an hindex of 3, co-authored 9 publications.
Chat about Author
Papers
Robust regularized extreme learning machine for regression using iteratively reweighted least squares
TL;DR: A unified model for robust regularized ELM regression using iteratively reweighted least squares (IRLS), and call it RELM-IRLS is proposed, which is stable and accurate for data with 0 ~ 40 % outlier levels, and can obtain a compact network because of the highly sparse output weights of the network.
90
Ranking Support Vector Machine with Kernel Approximation
TL;DR: Experimental results demonstrate that the proposed fast ranking algorithm based on kernel approximation gets a much faster training speed than kernel RankSVM and achieves comparable or better performance over state-of-the-art ranking algorithms.
LightQNet: Lightweight Deep Face Quality Assessment for Risk-Controlled Face Recognition
TL;DR: In this article, a pairwise binary quality pseudo-label is generated based on the face similarity score without additional manual annotation, and a lightweight quality network is trained by performing knowledge distillation on the quality prediction branch of the face recognition network.
13
Target relational attention-oriented knowledge graph reasoning
TL;DR: This work proposes a hierarchical attention mechanism to aggregate the information of multi-hop neighbors, and to thereby obtain a better node-embedding representation, (with high-order propagation characteristics) and relieves over-smoothing to a certain extent.
12
Fast and reliable probabilistic face embeddings based on constrained data uncertainty estimation
TL;DR: Chan et al. as mentioned in this paper proposed a probabilistic face embedding method to improve the robustness and speed of PFE by using a one-dimensional variance to approximate the data uncertainty of face feature.
9