2 citations · 2 across the 2 of their papers we have counts for
5 papers
HAROOD: A Benchmark for Out-of-distribution Generalization in Sensor-based Human Activity Recognition
Wang Lu, Yao Zhu, Jindong Wang
Sensor-based human activity recognition (HAR) mines activity patterns from the time-series sensory data. In realistic scenarios, variations across individuals, devices, environment…
Emotion Recognition in Signers
Kotaro Funakoshi, Yaoxiong Zhu
Recognition of signers' emotions suffers from one theoretical challenge and one practical challenge, namely, the overlap between grammatical and affective facial expressions and th…
Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application
Chuanpeng Yang, Wang Lu, Yao Zhu +5
Large Language Models (LLMs) have showcased exceptional capabilities in various domains, attracting significant interest from both academia and industry. Despite their impressive p…
Advancing Out-of-Distribution Detection through Data Purification and Dynamic Activation Function Design
Yingrui Ji, Yao Zhu, Zhigang Li +3
In the dynamic realms of machine learning and deep learning, the robustness and reliability of models are paramount, especially in critical real-world applications. A fundamental c…
Enhancing Few-shot CLIP with Semantic-Aware Fine-Tuning
Yao Zhu, Yuefeng Chen, Wei Wang +7
Learning generalized representations from limited training samples is crucial for applying deep neural networks in low-resource scenarios. Recently, methods based on Contrastive La…