33 citations · 98 across the 14 of their papers we have counts for
14 papers
Audio-Driven Dubbing for User Generated Contents via Style-Aware Semi-Parametric Synthesis
Linsen Song, Wayne Wu, Chaoyou Fu +2
Existing automated dubbing methods are usually designed for Professionally Generated Content (PGC) production, which requires massive training data and training time to learn a per…
Learning Cross-modality Information Bottleneck Representation for Heterogeneous Person Re-Identification
Haichao Shi, Mandi Luo, Xiao-Yu Zhang +1
Visible-Infrared person re-identification (VI-ReID) is an important and challenging task in intelligent video surveillance. Existing methods mainly focus on learning a shared featu…
Boosting Fast and High-Quality Speech Synthesis with Linear Diffusion
Haogeng Liu, Tao Wang, Jie Cao +2
Denoising Diffusion Probabilistic Models have shown extraordinary ability on various generative tasks. However, their slow inference speed renders them impractical in speech synthe…
Learning-to-Rank Meets Language: Boosting Language-Driven Ordering Alignment for Ordinal Classification
Rui Wang, Peipei Li, Huaibo Huang +3
We present a novel language-driven ordering alignment method for ordinal classification. The labels in ordinal classification contain additional ordering relations, making them pro…
Lightweight Vision Transformer with Bidirectional Interaction
Qihang Fan, Huaibo Huang, Xiaoqiang Zhou +1
Recent advancements in vision backbones have significantly improved their performance by simultaneously modeling images' local and global contexts. However, the bidirectional inter…
Rethinking Local Perception in Lightweight Vision Transformer
Qihang Fan, Huaibo Huang, Jiyang Guan +1
Vision Transformers (ViTs) have been shown to be effective in various vision tasks. However, resizing them to a mobile-friendly size leads to significant performance degradation. T…