A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends

J Gui, T Chen, J Zhang, Q Cao, Z Sun… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Deep supervised learning algorithms typically require a large volume of labeled data to
achieve satisfactory performance. However, the process of collecting and labeling such data …

Preserving integrity in online social networks

A Halevy, C Canton-Ferrer, H Ma, U Ozertem… - Communications of the …, 2022 - dl.acm.org
Preserving integrity in online social networks Page 1 92 COMMUNICATIONS OF THE ACM |
FEBRUARY 2022 | VOL. 65 | NO. 2 review articles THE GOAL OF online social networks is to …

Disentangled representation learning

X Wang, H Chen, Z Wu, W Zhu - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Disentangled Representation Learning (DRL) aims to learn a model capable of identifying
and disentangling the underlying factors hidden in the observable data in representation …

Progressive disentangled representation learning for fine-grained controllable talking head synthesis

D Wang, Y Deng, Z Yin, HY Shum… - Proceedings of the …, 2023 - openaccess.thecvf.com
We present a novel one-shot talking head synthesis method that achieves disentangled and
fine-grained control over lip motion, eye gaze&blink, head pose, and emotional expression …

One-shot talking face generation from single-speaker audio-visual correlation learning

S Wang, L Li, Y Ding, X Yu - Proceedings of the AAAI Conference on …, 2022 - ojs.aaai.org
Audio-driven one-shot talking face generation methods are usually trained on video
resources of various persons. However, their created videos often suffer unnatural mouth …

High-fidelity and freely controllable talking head video generation

Y Gao, Y Zhou, J Wang, X Li… - Proceedings of the …, 2023 - openaccess.thecvf.com
Talking head generation is to generate video based on a given source identity and target
motion. However, current methods face several challenges that limit the quality and …

Deepfake generation and detection: A benchmark and survey

G Pei, J Zhang, M Hu, Z Zhang, C Wang, Y Wu… - ar** methods mainly rely on GAN frameworks, but
recent focus has shifted to pre-trained diffusion models for their superior generation …

Region-aware face swap**

C Xu, J Zhang, M Hua, Q He, Z Yi… - Proceedings of the …, 2022 - openaccess.thecvf.com
This paper presents a novel Region-Aware Face Swap** (RAFSwap) network to achieve
identity-consistent harmonious high-resolution face generation in a local-global manner: 1) …

Talking head generation with probabilistic audio-to-visual diffusion priors

Z Yu, Z Yin, D Zhou, D Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
We introduce a novel framework for one-shot audio-driven talking head generation. Unlike
prior works that require additional driving sources for controlled synthesis in a deterministic …