4 accepted papers
We propose a multimodal-driven framework for high-fidelity long-term digital human animation termed Soul, which generates semantically coherent videos from a single-frame portrait image, text prompts, and audio, achieving precise lip synchronization, vivid facial expressions, and robust identity pre
Dataset distillation (DD) condenses key information from large-scale datasets into smaller synthetic datasets, reducing storage and computational costs for training networks. However, recent research has primarily focused on image classification tasks, with limited expansion to detection and segment…
Existing multi-label knowledge distillation methods simply use regression or single-label classification methods without fully exploiting the essence of multi-label classification, resulting in student models’ inadequate performance and poor functional similarity to teacher models. In this paper, we…
Video-text retrieval has widespread applications in economic and security domains, making it crucial to evaluate its robustness through adversarial attack. However, the existing research in this field is inadequate. In this paper, we first introduce adversarial attack to this task. By leveraging the…