5 papers
Omnimodal Dataset Distillation via High-order Proxy Alignment
Yuxuan Gao, Xiaohao Liu, Xiaobo Xia +1
Dataset distillation compresses large-scale datasets into compact synthetic sets while preserving training performance, but existing methods are largely restricted to single-modal…
WRF4CIR: Weight-Regularized Fine-Tuning Network for Composed Image Retrieval
Yizhuo Xu, Chaojian Yu, Yuanjie Shao +3
Composed Image Retrieval (CIR) task aims to retrieve target images based on reference images and modification texts. Current CIR methods primarily rely on fine-tuning vision-langua…
Immunizing 3D Gaussian Generative Models Against Unauthorized Fine-Tuning via Attribute-Space Traps
Jianwei Zhang, Sihan Cao, Chaoning Zhang +7
Recent large-scale generative models enable high-quality 3D synthesis. However, the public accessibility of pre-trained weights introduces a critical vulnerability. Adversaries can…
EvAnimate: Event-conditioned Image-to-Video Generation for Human Animation
Qiang Qu, Ming Li, Xiaoming Chen +1
Conditional human animation traditionally animates static reference images using pose-based motion cues extracted from video data. However, these video-derived cues often suffer fr…
NVS-SQA: Exploring Self-Supervised Quality Representation Learning for Neurally Synthesized Scenes without References
Qiang Qu, Yiran Shen, Xiaoming Chen +3
Neural View Synthesis (NVS), such as NeRF and 3D Gaussian Splatting, effectively creates photorealistic scenes from sparse viewpoints, typically evaluated by quality assessment met…