- 发布时间:2023-11-23
- 作者:光明实验室
- 浏览:4469次
姜文浩 研究员
邮箱:jiangwenhao@gml.ac.cn
研究领域:
生成式大模型相关领域,比如大模型结构优化、大模型基本能力优化、基于大模型的多模态理解和生成,大模型与具身智能结合等。研究成果上线于QQ空间、微信“搜一搜”、腾讯广告文案助手以及腾讯广告推荐等业务。
发表论文论著:
部分论文如下,完整列表请查看Google Scholar:
1. VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix.
Teng Wang, Wenhao Jiang, Zhichao Lu, Feng Zheng, Ran Cheng, Chengguo Yin, Ping Luo.
ICML 2022. [PDF]
2. DynaMixer: A Vision MLP Architecture with Dynamic Mixing.
Ziyu Wang, Wenhao Jiang, Yiming Zhu, Li Yuan, Yibing Song, and Wei Liu.
ICML 2022. [PDF] [CODE]
3. VideoMoCo: Contrastive video representation learning with temporally adversarial examples.
Tian Pan, Yibing Song, Tianyu Yang, Wenhao Jiang, Wei Liu.
CVPR 2021. [PDF][CODE]
4. Learning Modality Interaction for Temporal Sentence Localization and Event Captioning in Videos.
Shaoxiang Chen, Wenhao Jiang, Wei Liu, Yu-Gang Jiang.
ECCV 2020. [PDF]
5. Controllable Video Captioning With POS Sequence Guidance Based on Gated Fusion Network.
Bairui Wang, Lin Ma, Wei Zhang, Wenhao Jiang, Jingwen Wang, Wei Liu.
ICCV 2019. [PDF]
6. Recurrent fusion network for image captioning.
Wenhao Jiang, Lin Ma, Yu-gang Jiang, Wei Liu, Tong Zhang.
ECCV 2018. [PDF][CODE]
7. Regularizing RNNs for caption generation by reconstructing the past with the present.
Xinpeng Chen, Lin Ma, Wenhao Jiang, Jian Yao, Wei Liu.
CVPR 2018. [PDF]
8. Bidirectional attentive fusion with context gating for dense video captioning.
Jingwen Wang, Wenhao Jiang, Lin Ma, Wei Liu, Yong Xu.
CVPR 2018. [PDF]
9. Real-time neural style transfer for videos.
Haozhi Huang, Hao Wang, Wenhan Luo, Lin Ma, Wenhao Jiang, Xiaolong Zhu, Zhifeng Li, Wei Liu.
CVPR 2017. [PDF]
申请专利:
已获得授权国内专利37项,美国专利11项,其他国家15项。