| Coordinate CNNs and LSTMs to categorize scene images with multi-views and multi-levels of abstraction S Bai, H Tang, S An Expert Systems with Applications 120, 298-309, 2019 | 27 | 2019 |
| LSTM and multiple CNNs based event image classification P Li, H Tang, J Yu, W Song Multimedia Tools and Applications 80 (20), 30743-30760, 2021 | 11 | 2021 |
| Softly combining an ensemble of classifiers learned from a single convolutional neural network for scene categorization S Bai, H Tang Applied Soft Computing 67, 183-196, 2018 | 11 | 2018 |
| Lightweight vision transformer with cross feature attention Y Zhao, H Tang, Y Jiang, Q Wu arXiv preprint arXiv:2207.07268, 2022 | 9 | 2022 |
| Categorizing scenes by exploring scene part information without constructing explicit models S Bai, H Tang Neurocomputing 281, 160-168, 2018 | 6 | 2018 |
| Parameter-Efficient Vision Transformer with Linear Attention Y Zhao, H Tang, Y Jiang, A Yong, Q Wu, J Wang 2023 IEEE International Conference on Image Processing (ICIP), 1275-1279, 2023 | 1 | 2023 |
| Merino: Entropy-driven Design for Generative Language Models on IoT Devices Y Zhao, M Lin, H Tang, Q Wu, J Wang arXiv preprint arXiv:2403.07921, 2024 | | 2024 |
| Class-Aware Contextual Information for Semantic Segmentation H Tang, Y Zhao, Y Jiang, Z Gan, Q Wu ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023 | | 2023 |
| MeRino: Entropy-driven Design for Mobile-friendly Generative Language Models Y Zhao, M Lin, H Tang, Q Wu, J Wang | | |
