5 papers
Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms
Muyang He, Hanzhong Guo, Junxiong Lin +1
The rapid evolution of video generation has enabled models to simulate complex physical dynamics and long-horizon causalities, positioning them as potential world simulators. Howev…
Interest Entanglement: The Hidden Barrier to Blind Super-Resolution Optimization
Junxiong Lin, Xinji Mai, Qianyu Guo +5
Fidelity and perceptual quality are two inherently competing and conflicting objectives in the image super-resolution (SR) task. Different loss functions focus on these objectives…
Customizing Video Portraits via Identity-ActionDecoupling
Junxiong Lin, Haoran Wang, Xinji Mai +4
Identity-Preserving Text-to-Video Generation (IPT2V) seeks to synthesize a temporally coherent video from a reference image and a textual description, while simultaneously preservi…
Component-aware Unsupervised Logical Anomaly Generation for Industrial Anomaly Detection
Xuan Tong, Yang Chang, Qing Zhao +9
Anomaly detection is critical in industrial manufacturing for ensuring product quality and improving efficiency in automated processes. The scarcity of anomalous samples limits tra…
D2SP: Dynamic Dual-Stage Purification Framework for Dual Noise Mitigation in Vision-based Affective Recognition
Haoran Wang, Xinji Mai, Zeng Tao +10
The contemporary state-of-the-art of Dynamic Facial Expression Recognition (DFER) technology facilitates remarkable progress by deriving emotional mappings of facial expressions fr…