10 papers
DynaForcing: Overcoming Dynamic Collapse in Self-Forcing Distillation for Streaming Avatar Generation
Yubo Huang, Sirui Zhao, Xinchen Yao +5
Audio-driven avatar generation requires realistic lip-sync, expressive motion, and real-time streaming. Recent work achieves the latter via self-forcing with Distribution Matching…
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…
EviDep: Uncertainty-Aware Multimodal Depression Estimation via Disentangled Evidential Learning
Fangyuan Liu, Sirui Zhao, Yangsong Zhang +7
Audio--visual recordings provide complementary cues for estimating depression severity, but their informativeness varies across time and modalities. Point predictions alone do not…
Checkerboard: Closed-Form and Data-Independent Trigger Design for Clean-Label Backdoor Attacks
Yi Yang, Jinyang Huang, Binbin Liu +6
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 maps triggered inpu…
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…
Adaptive Attribute-Decoupled Encryption for Trusted Respiratory Monitoring in Resource-Limited Consumer Healthcare
Xinyu Li, Jinyang Huang, Feng-Qi Cui +4
Respiratory monitoring is an extremely important task in modern medical services. Due to its significant advantages, e.g., non-contact, radar-based respiratory monitoring has attra…
UniGeo: A Unified 3D Indoor Object Detection Framework Integrating Geometry-Aware Learning and Dynamic Channel Gating
Xing Yi, Jinyang Huang, Feng-Qi Cui +4
The growing adoption of robotics and augmented reality in real-world applications has driven considerable research interest in 3D object detection based on point clouds. While prev…
ReMA: A Training-Free Plug-and-Play Mixing Augmentation for Video Behavior Recognition
Feng-Qi Cui, Jinyang Huang, Sirui Zhao +4
Video behavior recognition demands stable and discriminative representations under complex spatiotemporal variations. However, prevailing data augmentation strategies for videos re…
Robust Low-Rank Sparse Framework for Video-Based Affective Computing
Feng-Qi Cui, Jinyang Huang, Sirui Zhao +4
Video-based Affective Computing (VAC), vital for emotion analysis and human-computer interaction, suffers from model instability and representational degradation due to complex emo…
Generalizing WiFi Gesture Recognition via Large-Model-Aware Semantic Distillation and Alignment
Feng-Qi Cui, Yu-Tong Guo, Tianyue Zheng +1
WiFi-based gesture recognition has emerged as a promising RF sensing paradigm for enabling non-contact and privacy-preserving human-computer interaction in AIoT environments. Howev…