3 citations · 9 across the 15 of their papers we have counts for
9 papers · 1 filter
PortraitTalk: Towards Customizable One-Shot Audio-to-Talking Face Generation
Fatemeh Nazarieh, Zhenhua Feng, Diptesh Kanojia +2
Audio-driven talking face generation is a challenging task in digital communication. Despite significant progress in the area, most existing methods concentrate on audio-lip synchr…
Rethinking Positive Pairs in Contrastive Learning
Jiantao Wu, Sara Atito, Zhenhua Feng +3
The training methods in AI do involve semantically distinct pairs of samples. However, their role typically is to enhance the between class separability. The actual notion of simil…
Probabilistically Aligned View-unaligned Clustering with Adaptive Template Selection
Wenhua Dong, Xiao-Jun Wu, Zhenhua Feng +3
In most existing multi-view modeling scenarios, cross-view correspondence (CVC) between instances of the same target from different views, like paired image-text data, is a crucial…
Single Image, Any Face: Generalisable 3D Face Generation
Wenqing Wang, Haosen Yang, Josef Kittler +1
The creation of 3D human face avatars from a single unconstrained image is a fundamental task that underlies numerous real-world vision and graphics applications. Despite the signi…
C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognition
Rongchang Li, Zhenhua Feng, Tianyang Xu +5
Compositional actions consist of dynamic (verbs) and static (objects) concepts. Humans can easily recognize unseen compositions using the learned concepts. For machines, solving su…
Investigating Self-Supervised Methods for Label-Efficient Learning
Srinivasa Rao Nandam, Sara Atito, Zhenhua Feng +2
Vision transformers combined with self-supervised learning have enabled the development of models which scale across large datasets for several downstream tasks like classification…
Pseudo Labelling for Enhanced Masked Autoencoders
Srinivasa Rao Nandam, Sara Atito, Zhenhua Feng +2
Masked Image Modeling (MIM)-based models, such as SdAE, CAE, GreenMIM, and MixAE, have explored different strategies to enhance the performance of Masked Autoencoders (MAE) by modi…
Revisiting RGBT Tracking Benchmarks from the Perspective of Modality Validity: A New Benchmark, Problem, and Solution
Zhangyong Tang, Tianyang Xu, Zhenhua Feng +4
RGBT tracking draws increasing attention because its robustness in multi-modal warranting (MMW) scenarios, such as nighttime and adverse weather conditions, where relying on a sing…
DailyMAE: Towards Pretraining Masked Autoencoders in One Day
Jiantao Wu, Shentong Mo, Sara Atito +3
Recently, masked image modeling (MIM), an important self-supervised learning (SSL) method, has drawn attention for its effectiveness in learning data representation from unlabeled…