Skip to main content

Research Repository

Advanced Search

Outputs (13)

A Probabilistic Zero-Shot Learning Method via Latent Nonnegative Prototype Synthesis of Unseen Classes (2019)
Journal Article
Zhang, H., Mao, H., Long, Y., Yang, W., & Shao, L. (2020). A Probabilistic Zero-Shot Learning Method via Latent Nonnegative Prototype Synthesis of Unseen Classes. IEEE Transactions on Neural Networks and Learning Systems, 31(7), 2361-2375. https://doi.org/10.1109/tnnls.2019.2955157

Zero-shot learning (ZSL), a type of structured multioutput learning, has attracted much attention due to its requirement of no training data for target classes. Conventional ZSL methods usually project visual features into semantic space and assign l... Read More about A Probabilistic Zero-Shot Learning Method via Latent Nonnegative Prototype Synthesis of Unseen Classes.

Semantic combined network for zero-shot scene parsing (2019)
Journal Article
Wang, Y., Zhang, H., Wang, S., Long, Y., & Yang, L. (2020). Semantic combined network for zero-shot scene parsing. IET Image Processing, 14(4), 757 -765. https://doi.org/10.1049/iet-ipr.2019.0870

Recently, image-based scene parsing has attracted increasing attention due to its wide application. However, conventional models can only be valid on images with the same domain of the training set and are typically trained using discrete and meaning... Read More about Semantic combined network for zero-shot scene parsing.

2D Pose-Based Real-Time Human Action Recognition With Occlusion-Handling (2019)
Journal Article
Angelini, F., Fu, Z., Long, Y., Shao, L., & Naqvi, S. M. (2020). 2D Pose-Based Real-Time Human Action Recognition With Occlusion-Handling. IEEE Transactions on Multimedia, 22(6), 1433-1446. https://doi.org/10.1109/tmm.2019.2944745

Human Action Recognition (HAR) for CCTV-oriented applications is still a challenging problem. Real-world scenarios HAR implementations is difficult because of the gap between Deep Learning data requirements and what the CCTV-based frameworks can offe... Read More about 2D Pose-Based Real-Time Human Action Recognition With Occlusion-Handling.

Few-Shot Image and Sentence Matching via Gated Visual-Semantic Embedding (2019)
Presentation / Conference Contribution
Huang, Y., Long, Y., & Wang, L. (2019, December). Few-Shot Image and Sentence Matching via Gated Visual-Semantic Embedding. Presented at Thirty-Second AAAI Conference on Artificial Intelligence

Word similarity and word relatedness are fundamental to natural language processing and more generally, understanding how humans relate concepts in semantic memory. A growing number of datasets are being proposed as evaluation benchmarks,however, the... Read More about Few-Shot Image and Sentence Matching via Gated Visual-Semantic Embedding.