High-compression tokenizers are essential for scaling latent image generative models. However, aggressive compression creates a fundamental tradeoff between reconstruction fidelity and generation efficiency: high compression image encoder always increases the learning difficulty of diffusion training, resulting in slow...
Xue-Zheng Huang, Ye Huang, Zi-Jun Liao et al.· 0 citations
A new completion paradigm that innovatively bridges advanced 2D generative models with unguided depth completion, enabling semantics-aware depth inference without real RGB inputs, and a pseudo-image semantic attention fusion module to adaptively extract informative semantic cues from pseudo-images while suppressing art...
Human‐centric sensing tasks such as visual sentiment analysis and smartphone‐based human activity recognition (HAR) exhibit strong client heterogeneity from feature, label, and concept shifts. Among these, concept shift—how individual users interpret and generate human‐centric signals—is particularly challenging yet...
Chang Liu, Ya-Peng Li, Zeng-Mao Wang et al.· CAAI Transactions on Intelli...· 0 citations
This paper introduces MAR-12, a novel framework that leverages Vision Language Models (VLMs) for meme detection and understanding in settings where humorous and hateful elements may coexist, and confirms that MAR-12 produces coherent and persuasive explanations.
Shanhong Liu, Pai Chet Ng, D. Soh et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
