papers

Publications (6)

cs.CV2023

Non-contact PPG Signal and Heart Rate Estimation with Multi-hierarchical Convolutional Network

Bin Li, Panpan Zhang, Jinye Peng +1

Heartbeat rhythm and heart rate (HR) are important physiological parameters of the human body. This study presents an efficient multi-hierarchical spatio-temporal convolutional net…

cs.CV2022

Unifying Graph Embedding Features with Graph Convolutional Networks for Skeleton-based Action Recognition

Dong Yang, Monica Mengqi Li, Hong Fu +3

Combining skeleton structure with graph convolutional networks has achieved remarkable performance in human action recognition. Since current research focuses on designing basic gr…

cs.CV2024

APLe: Token-Wise Adaptive for Multi-Modal Prompt Learning

Guiming Cao, Kaize Shi, Hong Fu +2

Pre-trained Vision-Language (V-L) models set the benchmark for generalization to downstream tasks among the noteworthy contenders. Many characteristics of the V-L model have been e…

cs.CV2021

Serial-parallel Multi-Scale Feature Fusion for Anatomy-Oriented Hand Joint Detection

Bin Li, Hong Fu, Ruimin Li +1

Accurate hand joints detection from images is a fundamental topic which is essential for many applications in computer vision and human computer interaction. This paper presents a…

cs.CV2023

Progression-Guided Temporal Action Detection in Videos

Chongkai Lu, Man-Wai Mak, Ruimin Li +2

We present a novel framework, Action Progression Network (APN), for temporal action detection (TAD) in videos. The framework locates actions in videos by detecting the action evolu…

cs.HC2022

PR-PL: A Novel Transfer Learning Framework with Prototypical Representation based Pairwise Learning for EEG-Based Emotion Recognition

Rushuang Zhou, Zhiguo Zhang, Hong Fu +7

Affective brain-computer interfaces based on electroencephalography (EEG) is an important branch in the field of affective computing. However, individual differences and noisy labe…