65 citations · 91 across the 11 of their papers we have counts for
4 papers · 1 filter
Learning Invariant Visual Representations for Compositional Zero-Shot Learning
Tian Zhang, Kongming Liang, Ruoyi Du +3
Compositional Zero-Shot Learning (CZSL) aims to recognize novel compositions using knowledge learned from seen attribute-object compositions in the training set. Previous works mai…
Multi-View Active Fine-Grained Recognition
Ruoyi Du, Wenqing Yu, Heqing Wang +4
As fine-grained visual classification (FGVC) being developed for decades, great works related have exposed a key direction -- finding discriminative local regions and revealing sub…
Caption Feature Space Regularization for Audio Captioning
Yiming Zhang, Hong Yu, Ruoyi Du +2
Audio captioning aims at describing the content of audio clips with human language. Due to the ambiguity of audio, different people may perceive the same audio differently, resulti…
Domain Generalization via Frequency-domain-based Feature Disentanglement and Interaction
Jingye Wang, Ruoyi Du, Dongliang Chang +2
Adaptation to out-of-distribution data is a meta-challenge for all statistical learning algorithms that strongly rely on the i.i.d. assumption. It leads to unavoidable labor costs…