A5050230765- Multimodal Machine Learning Applications
- Anomaly Detection Techniques and Applications
- Video Analysis and Summarization
- Network Security and Intrusion Detection
- Advanced Image and Video Retrieval Techniques
- Topic Modeling
- Influenza Virus Research Studies
- Pediatric health and respiratory diseases
- Fault Detection and Control Systems
- Smoking Behavior and Cessation
- Human Pose and Action Recognition
- Adversarial Robustness in Machine Learning
Beijing University of Posts and Telecommunications
2024
Zhejiang University
2023
Sir Run Run Shaw Hospital
2023
Out-of-distribution (OOD) detection is vital to safety-critical machine learning applications and has thus been extensively studied, with a plethora of methods developed in the literature. However, field currently lacks unified, strictly formulated, comprehensive benchmark, which often results unfair comparisons inconclusive results. From problem setting perspective, OOD closely related neighboring fields including anomaly (AD), open set recognition (OSR), model uncertainty, since for one...
China has approximately 300 million current smokers, and smoking cessation services are limited. This study aimed to assess the efficacy of a Cognitive Behavioral Theory-based intervention ('WeChat WeQuit') via most popular social media platform in China, WeChat.A parallel, single-blind, two-arm randomised controlled trial was conducted WeChat between March 19, 2020 November 16, 2022. Chinese-speaking adult smokers (n = 2000) willing quit within one month were recruited 1:1 ratio. The group...
Surprising videos, such as funny clips, creative performances, or visual illusions, attract significant attention. Enjoyment of these videos is not simply a response to stimuli; rather, it hinges on the human capacity understand (and appreciate) commonsense violations depicted in videos. We introduce FunQA, challenging video question-answering (QA) dataset specifically designed evaluate and enhance depth reasoning based counter-intuitive fun Unlike most QA benchmarks which focus less...