Dr Yang Long's Outputs (6)

Imaginary-Connected Embedding in Complex Space for Unseen Attribute-Object Discrimination (2024)
Journal Article
Jiang, C., Wang, S., Long, Y., Li, Z., Zhang, H., & Shao, L. (online). Imaginary-Connected Embedding in Complex Space for Unseen Attribute-Object Discrimination. IEEE Transactions on Pattern Analysis and Machine Intelligence, https://doi.org/10.1109/tpami.2024.3487631

Compositional Zero-Shot Learning (CZSL) aims to recognize novel compositions of seen primitives. Prior studies have attempted to either learn primitives individually (non-connected) or establish dependencies among them in the composition (fully-conne... Read More about Imaginary-Connected Embedding in Complex Space for Unseen Attribute-Object Discrimination.

SID-NERF: Few-Shot Nerf Based on Scene Information Distribution (2024)
Presentation / Conference Contribution
Li, Y., Wan, F., & Long, Y. (2024, July). SID-NERF: Few-Shot Nerf Based on Scene Information Distribution. Presented at 2024 IEEE International Conference on Multimedia and Expo (ICME), Niagara Falls, ON, Canada

The novel view synthesis from a limited set of images is a significant research focus. Traditional NeRF methods, relying mainly on color supervision, struggle with accurate scene geometry reconstruction when faced with sparse input images, leading to... Read More about SID-NERF: Few-Shot Nerf Based on Scene Information Distribution.

CTNeRF: Cross-time Transformer for dynamic neural radiance field from monocular video (2024)
Journal Article
Miao, X., Bai, Y., Duan, H., Wan, F., Huang, Y., Long, Y., & Zheng, Y. (2024). CTNeRF: Cross-time Transformer for dynamic neural radiance field from monocular video. Pattern Recognition, 156, Article 110729. https://doi.org/10.1016/j.patcog.2024.110729

The goal of our work is to generate high-quality novel views from monocular videos of complex and dynamic scenes. Prior methods, such as DynamicNeRF, have shown impressive performance by leveraging time-varying dynamic radiation fields. However, thes... Read More about CTNeRF: Cross-time Transformer for dynamic neural radiance field from monocular video.

Leveraging Self-Distillation and Disentanglement Network to Enhance Visual–Semantic Feature Consistency in Generalized Zero-Shot Learning (2024)
Journal Article
Liu, X., Wang, C., Yang, G., Wang, C., Long, Y., Liu, J., & Zhang, Z. (2024). Leveraging Self-Distillation and Disentanglement Network to Enhance Visual–Semantic Feature Consistency in Generalized Zero-Shot Learning. Electronics, 13(10), Article 1977. https://doi.org/10.3390/electronics13101977

Generalized zero-shot learning (GZSL) aims to simultaneously recognize both seen classes and unseen classes by training only on seen class samples and auxiliary semantic descriptions. Recent state-of-the-art methods infer unseen classes based on sema... Read More about Leveraging Self-Distillation and Disentanglement Network to Enhance Visual–Semantic Feature Consistency in Generalized Zero-Shot Learning.

Towards Cognition-Aligned Visual Language Models via Zero-Shot Instance Retrieval (2024)
Journal Article
Ma, T., Organisciak, D., Ma, W., & Long, Y. (2024). Towards Cognition-Aligned Visual Language Models via Zero-Shot Instance Retrieval. Electronics, 13(9), Article 1660. https://doi.org/10.3390/electronics13091660

The pursuit of Artificial Intelligence (AI) that emulates human cognitive processes is a cornerstone of ethical AI development, ensuring that emerging technologies can seamlessly integrate into societal frameworks requiring nuanced understanding and... Read More about Towards Cognition-Aligned Visual Language Models via Zero-Shot Instance Retrieval.

Wearable-based behaviour interpolation for semi-supervised human activity recognition (2024)
Journal Article
Duan, H., Wang, S., Ojha, V., Wang, S., Huang, Y., Long, Y., …Zheng, Y. (2024). Wearable-based behaviour interpolation for semi-supervised human activity recognition. Information Sciences, 665, Article 120393. https://doi.org/10.1016/j.ins.2024.120393

While traditional feature engineering for Human Activity Recognition (HAR) involves a trial-and-error process, deep learning has emerged as a preferred method for high-level representations of sensor-based human activities. However, most deep learnin... Read More about Wearable-based behaviour interpolation for semi-supervised human activity recognition.