4 papers
Dual-Stream Collaborative Transformer for Image Captioning
Jun Wan, Jun Liu, Zhihui lai +1
Current region feature-based image captioning methods have progressed rapidly and achieved remarkable performance. However, they are still prone to generating irrelevant descriptio…
Supervision-by-Hallucination-and-Transfer: A Weakly-Supervised Approach for Robust and Precise Facial Landmark Detection
Jun Wan, Yuanzhi Yao, Zhihui Lai +3
High-precision facial landmark detection (FLD) relies on high-resolution deep feature representations. However, low-resolution face images or the compression (via pooling or stride…
FGTBT: Frequency-Guided Task-Balancing Transformer for Unified Facial Landmark Detection
Jun Wan, Xinyu Xiong, Ning Chen +3
Recently, deep learning based facial landmark detection (FLD) methods have achieved considerable success. However, in challenging scenarios such as large pose variations, illuminat…
Precise Facial Landmark Detection by Dynamic Semantic Aggregation Transformer
Jun Wan, He Liu, Yujia Wu +3
At present, deep neural network methods have played a dominant role in face alignment field. However, they generally use predefined network structures to predict landmarks, which t…