Recommended citation: Liang, Y., Hong, F., Lin, Q., Bi, S., & Feng, L. (2017, July). Optimization of robot path planning parameters based on genetic algorithm. In 2017 IEEE International Conference on Real-time Computing and Robotics (RCAR) (pp. 529-534). IEEE.

Learning to Learn Relation for Important People Detection in Still Images

Published in International Conference on Computer Vision and Pattern Recognition, 2019

In this work, we propose a deep imPOrtance relatIon NeTwork (POINT) that combines both relation modeling and feature learning.

Recommended citation: Wei-Hong Li, Fa-Ting Hong, and Wei-Shi Zheng. Learning to learn relation for important people detection in still images. In Computer Vision and Pattern Recognition, 2019.

Learning to Detect Important People in Unlabelled Images for Semi-supervised Important People Detection

Published in International Conference on Computer Vision and Pattern Recognition, 2020

In this work, we study semi-supervised learning in the context of important people detection and propose a semi-supervised learning method for this task.

Recommended citation: Fa-Ting Hong, Wei-Hong Li and Wei-Shi Zheng. Learning to Detect Important People in Unlabelled Images for Semi-supervised Important People Detection. In Computer Vision and Pattern Recognition, 2020.

MINI-Net: Multiple Instance Ranking Network for Video Highlight Detection

Published in European Conference on Computer Vision, 2020

We address the weakly supervised video highlight detectionproblem for learning to detect the segments that are more attractivein training videos given their video event label but without expensivesupervision of manually annotating highlight segments.

Recommended citation: Fa-Ting Hong, Xuanteng Huang, Wei-Hong Li, and Wei-Shi Zheng. MINI-Net: Multiple Instance Ranking Networkfor Video Highlight Detection. In European Conference on Computer Vision (ECCV), 2020.

Hybrid Dynamic-static Context-aware Attention Network for Action Assessment in Long Videos

Published in ACM International Conference on Multimedia, 2020

In this work, we present a novel hybrid dynAmic-static Context-aware attenTION NETwork (ACTION-NET) for action assessment in long videos

Recommended citation: Ling-An Zeng, Fa-Ting Hong, Wei-Shi Zheng, Qi-Zhi Yu, Wei Zeng, Yao-Wei Wang, and Jian-Huang Lai. Hybrid Dynamic-static Context-aware Attention Network for Action Assessment in Long Videos. Proc. of ACM International Conference on Multimedia (ACM MM), 2020.

MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection

Published in IEEE International Conference on Computer Vision and Pattern Recognition, 2021

In this work, we develop a multiple instance self-training framework (MIST) to efficiently refine task-specific discriminative representations with only video-level annotations.

Recommended citation: Jia-Chang Feng, Fa-Ting Hong and Wei-Shi Zheng. MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection, Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition. 2021.

Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization

Published in ACM International Conference on Multimedia, 2021

In this work, we explore feature re-calibration for action localization to reduce the redundancy. A cross-modal consensus network is proposed to tackle this problem.

Recommended citation: Fa-Ting Hong, Jia-Chang Feng, Dan Xu, Ying Shan, Wei-Shi Zheng. Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization. ACM International Conference on Multimedia, 2021.