[1] Pengjie Tang, Jiayu Zhang, Hanli Wang, Yunlan Tan, Yun Yi. SRVC-LA: Sparse regularization of visual context and latent attention based model for video description. Neurocomputing, 2025, 630: 1-13. [2] Pengjie Tang, Yunlan Tan, Wenlang Luo. Visual and language semantic hybrid enhancement and complementary for video description. Neural Computing and Applications. 2022, 34: 5959-5977. [3] Hanli Wang, Pengjie Tang（共同一作）, Qinyu Li, Meng Cheng. Emotion expression with fact transfer for video description. IEEE Transactions on Multimedia, 2022, 24: 715-727. [4] 汤鹏杰, 王瀚漓. 从视频到语言：视频标题生成与描述研究综述. 自动化学报, 2022, 48(2): 375-397. [5] Yu Long, Pengjie Tang(通讯作者), Zhihua Wei, et al. RepeatPadding: Balancing words and sentence length for language comprehension in visual question answering. Information Sciences, 2020, 529: 166-178. [6] Pengjie Tang, Yunlan Tan, Jinzhong Li, and Bin Tan. Translating video into language by enhancing visual and language representations, Journal of Visual Communication of Image Representation，2020, 72(2020). [7] Pengjie Tang, Hanli Wang, Qinyu Li. Rich visual and language representation with complementary semantics for video captioning. ACM Transactions on Multimedia Computing, Communications, and Applications, 2019, 15(2):31(1-23). [8] Pengjie Tang, Hanli Wang, Sam Kwong. Deep sequential fusion LSTM network for image description. Neurocomputing, 2018, 312(2018): 154-164. [9] Pengjie Tang, Hanli Wang, Sam Kwong. G-MS2F: GoogLeNet based multistage feature fusion of deep CNN for scene recognition. Neurocomputing, 2017, 225(2017): 188-197. [10] Pengjie Tang, Hanli Wang, Hanzhang Wang, Kaisheng Xu. Richer semantic visual and language representation for video captioning. In Proceedings of International Conference on Multimedia, 2017, 10: 1871-1876. [11] 王瀚漓，汤鹏杰，李秦渝，“一种基于事实转移的情感嵌入视频描述方法”，专利号：ZL201910659357.3， 2021. 09. [12] 王瀚漓，汤鹏杰，“一种基于深度LSTM网络的图像描述生成方法”，专利号: ZL201611022441.7，2023. 04. |
