Procc: Progressive cross-primitive compatibility for open-world compositional zero-shot learning

Y Chen, J Guo, T He, X Lu, L Wang - Proceedings of the 32nd ACM …, 2024 - dl.acm.org

Skeleton-based zero-shot action recognition aims to recognize unknown human actions
based on the learned priors of the known skeleton-based actions and a semantic descriptor …

被引用次数：4 相关文章所有 2 个版本

[PDF] arxiv.org

On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Survey

J Guo, Z Rao, Z Chen, S Guo, J Zhou, D Tao - arXiv preprint arXiv …, 2024 - arxiv.org

Zero-shot image recognition (ZSIR) aims at empowering models to recognize and reason in
unseen domains via learning generalized knowledge from limited data in the seen domain …

被引用次数：1 相关文章所有 2 个版本

[PDF] arxiv.org

Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition

Y Chen, J Guo, S Guo, D Tao - arXiv preprint arXiv:2411.11288, 2024 - arxiv.org

Zero-shot skeleton action recognition is a non-trivial task that requires robust unseen
generalization with prior knowledge from only seen classes and shared semantics. Existing …

Dual Expert Distillation Network for Generalized Zero-Shot Learning

Z Rao, J Guo, X Lu, J Liang, J Zhang, H Wang… - arXiv preprint arXiv …, 2024 - arxiv.org

Zero-shot learning has consistently yielded remarkable progress via modeling nuanced one-
to-one visual-attribute correlation. Existing studies resort to refining a uniform mapping …

被引用次数：2 相关文章所有 2 个版本

[PDF] arxiv.org

Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learning

X Yan, S Feng, Y Zhang, J Yang, Y Lin… - arXiv preprint arXiv …, 2024 - arxiv.org

Compositional zero-shot learning (CZSL) aims to recognize novel compositions of attributes
and objects learned from seen compositions. Previous works disentangle attribute and …

Hybrid Discriminative Attribute-Object Embedding Network for Compositional Zero-Shot Learning

Y Liu, X Wang, J Du, X Gao, J Han - arXiv preprint arXiv:2412.00121, 2024 - arxiv.org

Compositional Zero-Shot Learning (CZSL) recognizes new combinations by learning from
known attribute-object pairs. However, the main challenge of this task lies in the complex …