Deyao Zhu
Citado por
Citado por
MiniGPT-4: Enhancing vision-language understanding with advanced large language models
D Zhu, J Chen, X Shen, X Li, M Elhoseiny
arXiv preprint arXiv:2304.10592, 2023
Motion forecasting with unlikelihood training in continuous space
D Zhu, M Zahran, LE Li, M Elhoseiny
Conference on Robot Learning, 1003-1012, 2022
Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectiveness of Implicit Maximum Likelihood Estimation
A Mohamed, D Zhu, W Vu, M Elhoseiny, C Claudel
European Conference on Computer Vision (ECCV) 2022, 2022
ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptions
D Zhu, J Chen, K Haydarov, X Shen, W Zhang, M Elhoseiny
arXiv preprint arXiv:2303.06594, 2023
Video ChatCaptioner: Towards the Enriched Spatiotemporal Descriptions
J Chen, D Zhu, K Haydarov, X Li, M Elhoseiny
arXiv preprint arXiv:2304.04227, 2023
Learning to disentangle latent physical factors for video prediction
D Zhu, M Munderloh, B Rosenhahn, J Stückler
Pattern Recognition: 41st DAGM German Conference, DAGM GCPR 2019, Dortmund …, 2019
HalentNet: Multimodal Trajectory Forecasting with Hallucinative Intents
D Zhu, M Zahran, LE Li, M Elhoseiny
International Conference on Learning Representations, 2021, 2021
Guiding Online Reinforcement Learning with Action-Free Offline Pretraining
D Zhu, Y Wang, J Schmidhuber, M Elhoseiny
arXiv preprint arXiv:2301.12876, 2023
Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learning
D Zhu, LE Li, M Elhoseiny
arXiv preprint arXiv:2206.04384, 2022
RelTransformer: Balancing the Visual Relationship Detection from Local Context, Scene and Memory
J Chen, A Agarwal, S Abdelkarim, D Zhu, M Elhoseiny
2022 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
CausalDyna: Improving Generalization of Dyna-style Reinforcement Learning via Counterfactual-Based Data Augmentation
D Zhu, LE Li, M Elhoseiny
O sistema não pode efectuar a operação agora. Tente mais tarde.
Artigos 1–11