Zobrazeno 1 - 10
of 1 237
pro vyhledávání: '"Li Ziqiang"'
3D-aware image generation necessitates extensive training data to ensure stable training and mitigate the risk of overfitting. This paper first considers a novel task known as One-shot 3D Generative Domain Adaptation (GDA), aimed at transferring a pr
Externí odkaz:
http://arxiv.org/abs/2410.08824
Autor:
Li, Jia, Yu, Yangchen, Chen, Yin, Zhang, Yu, Jia, Peng, Xu, Yunbo, Li, Ziqiang, Wang, Meng, Hong, Richang
Engagement estimation plays a crucial role in understanding human social behaviors, attracting increasing research interests in fields such as affective computing and human-computer interaction. In this paper, we propose a Dialogue-Aware Transformer
Externí odkaz:
http://arxiv.org/abs/2410.08470
Autor:
Wang, Yunnan, Li, Ziqiang, Zhang, Zequn, Zhang, Wenyao, Xie, Baao, Liu, Xihui, Zeng, Wenjun, Jin, Xin
There has been exciting progress in generating images from natural language or layout conditions. However, these methods struggle to faithfully reproduce complex scenes due to the insufficient modeling of multiple objects and their relationships. To
Externí odkaz:
http://arxiv.org/abs/2410.00447
With the burgeoning advancements in the field of natural language processing (NLP), the demand for training data has increased significantly. To save costs, it has become common for users and businesses to outsource the labor-intensive task of data c
Externí odkaz:
http://arxiv.org/abs/2408.11587
Drawing on recent advancements in diffusion models for text-to-image generation, identity-preserved personalization has made significant progress in accurately capturing specific identities with just a single reference image. However, existing method
Externí odkaz:
http://arxiv.org/abs/2403.11781
The proliferation of malicious deepfake applications has ignited substantial public apprehension, casting a shadow of doubt upon the integrity of digital media. Despite the development of proficient deepfake detection mechanisms, they persistently de
Externí odkaz:
http://arxiv.org/abs/2403.06610
Autor:
Jin, Xin, Li, Bohan, Xie, BAAO, Zhang, Wenyao, Liu, Jinming, Li, Ziqiang, Yang, Tao, Zeng, Wenjun
Representation disentanglement may help AI fundamentally understand the real world and thus benefit both discrimination and generation tasks. It currently has at least three unresolved core issues: (i) heavy reliance on label annotation and synthetic
Externí odkaz:
http://arxiv.org/abs/2402.02346
Dynamical behaviors of complex interacting systems, including brain activities, financial price movements, and physical collective phenomena, are associated with underlying interactions between the system's components. The issue of uncovering interac
Externí odkaz:
http://arxiv.org/abs/2401.16755
Although few-shot action recognition based on metric learning paradigm has achieved significant success, it fails to address the following issues: (1) inadequate action relation modeling and underutilization of multi-modal information; (2) challenges
Externí odkaz:
http://arxiv.org/abs/2401.04150
With the boom in the natural language processing (NLP) field these years, backdoor attacks pose immense threats against deep neural network models. However, previous works hardly consider the effect of the poisoning rate. In this paper, our main obje
Externí odkaz:
http://arxiv.org/abs/2311.13957