As visual data are increasingly consumed by recognition models, vision language systems, and robotic agents, perceptual quality alone cannot fully reflect downstream utility. Mild visual distortions may remove boundary, color, semantic, or affordance cues important to machine perception, while stronger perceptual degra...
Zhi-Meng Huang, Rong-Ao Yuan, Jia-Qi Zhang et al.· Proceedings of the 34th ACM...· 0 citations
3D Gaussian Splatting (3DGS) has become a promising representation for real-time novel view synthesis and 3D scene reconstruction. For practical deployment, recent studies have explored pose-free feed-forward 3DGS, which reconstructs Gaussian representations directly from unposed input images. However, these methods re...
Xiao-Han Lu, Jia-Qi Zhang, Wei-Jia Jiang et al.· 0 citations
Depression ranks as one of the most prevalent psychological disorders and has received growing attention. Currently, there are two primary challenges in automatic video depression detection: the scarcity of labeled depressed data and effective feature representations characterizing human depression. To address these ch...
Zhe-Wei Fang, Kai-Yin Lian, Shi-Qing Zhang et al.· IEEE Transactions on Pattern...· 0 citations
CoViST is proposed, a training-free framework that represents a compressed image as a composable visual state that retains its interpretation under successive reductions, enabling the same formulation to support both fixed compression before prefill and progressive compression within the decoder.
Qi Zhang, Xian-Dong Meng, Rong-Gang Wang et al.· arXiv.org· 0 citations
Protein design is moving beyond structural correctness toward function-aware design, yet existing generative models typically treat dynamics as a downstream property estimated through simulation or prediction after structure generation. Using MD trajectories as a generative target is also undesirable because stochastic...
Yu-Tian Liu, Mu-Jie Lin, Lan-Qian Zhang et al.· 0 citations
This work proposes CodecArena, the first vision-language framework for video coding quality assessment, casting codec evaluation as source-conditioned comparative reasoning between a reference and its reconstructions, and achieves state-of-the-art agreement with human judgments on source-disjoint content across diverse...
Jiaye Fu, Wei-Qi Li, Qiankun Gao et al.· 0 citations