13 papers
Diversity Matters: Distributional Feature Coverage Sample Selection for Data-Efficient Backdoor Attacks
Yi Yang, Xiaoke Chen, Jinyang Huang +6
Backdoor attacks compromise training data so that a model retains clean accuracy but predicts an attacker-chosen target on triggered inputs. At very low poisoning rates, only a few…
Every Subtlety Counts: Fine-grained Person Independence Micro-Action Recognition via Distributionally Robust Optimization
Feng-Qi Cui, Jinyang Huang, Anyang Tong +6
Micro-action Recognition is vital for psychological assessment and human-computer interaction. However, existing methods often fail in real-world scenarios because inter-person var…
EviDep: Trustworthy Multimodal Depression Estimation via Disentangled Evidential Learning
Fangyuan Liu, Sirui Zhao, Zeyu Zhang +6
Automated multimodal depression estimation in unconstrained environments is inherently challenged by naturalistic noise and complex behavioral variability. Prevailing deterministic…
Checkerboard: A Simple, Effective, Efficient and Learning-free Clean Label Backdoor Attack with Low Poisoning Budget
Yi Yang, Jinyang Huang, Binbin Liu +5
Backdoor attacks threaten the deep learning supply chain by poisoning a small fraction of the training data so that a model behaves normally on clean inputs but misclassifies trigg…
Dual-Path Learning based on Frequency Structural Decoupling and Regional-Aware Fusion for Low-Light Image Super-Resolution
Ji-Xuan He, Jia-Cheng Zhao, Feng-Qi Cui +5
Low-light image super-resolution (LLISR) is essential for restoring fine visual details and perceptual quality under insufficient illumination conditions with ubiquitous low-resolu…
TAAC: A gate into Trustable Audio Affective Computing
Xintao Hu, Feng-Qi Cui
With the emergence of AI techniques for depression diagnosis, the conflict between high demand and limited supply for depression screening has been significantly alleviated. Among…