Picture for Difei Gao

Difei Gao

An Efficient COarse-to-fiNE Alignment Framework @ Ego4D Natural Language Queries Challenge 2022

Nov 16, 2022
Zhijian Hou, Wanjun Zhong, Lei Ji, Difei Gao, Kun Yan, Wing-Kwong Chan, Chong-Wah Ngo, Zheng Shou, Nan Duan

Figure 1 for An Efficient COarse-to-fiNE Alignment Framework @ Ego4D Natural Language Queries Challenge 2022

Figure 2 for An Efficient COarse-to-fiNE Alignment Framework @ Ego4D Natural Language Queries Challenge 2022

Figure 3 for An Efficient COarse-to-fiNE Alignment Framework @ Ego4D Natural Language Queries Challenge 2022

Figure 4 for An Efficient COarse-to-fiNE Alignment Framework @ Ego4D Natural Language Queries Challenge 2022

* Technical report for ECCV 2022 Ego4D workshop, 4 pages, 2 figures, 2 tables. arXiv admin note: substantial text overlap with arXiv:2209.10918

Access Paper or Ask Questions

CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding

Sep 22, 2022
Zhijian Hou, Wanjun Zhong, Lei Ji, Difei Gao, Kun Yan, Wing-Kwong Chan, Chong-Wah Ngo, Zheng Shou, Nan Duan

Figure 1 for CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding

Figure 2 for CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding

Figure 3 for CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding

Figure 4 for CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding

* Preprint. 9 pages, 5 figures, 3 tables

Access Paper or Ask Questions

Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task

Aug 29, 2022
Stan Weixian Lei, Difei Gao, Jay Zhangjie Wu, Yuxuan Wang, Wei Liu, Mengmi Zhang, Mike Zheng Shou

Figure 1 for Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task

Figure 2 for Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task

Figure 3 for Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task

Figure 4 for Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task

* 18 pages, 13 figures

Access Paper or Ask Questions

Egocentric Video-Language Pretraining @ Ego4D Challenge 2022

Jul 04, 2022
Kevin Qinghong Lin, Alex Jinpeng Wang, Mattia Soldan, Michael Wray, Rui Yan, Eric Zhongcong Xu, Difei Gao, Rongcheng Tu, Wenzhe Zhao, Weijie Kong, Chengfei Cai, Hongfa Wang, Dima Damen, Bernard Ghanem, Wei Liu, Mike Zheng Shou

Figure 1 for Egocentric Video-Language Pretraining @ Ego4D Challenge 2022

Figure 2 for Egocentric Video-Language Pretraining @ Ego4D Challenge 2022

Figure 3 for Egocentric Video-Language Pretraining @ Ego4D Challenge 2022

Figure 4 for Egocentric Video-Language Pretraining @ Ego4D Challenge 2022

* To appeared in CVPRW22. 4 pages, 2 figures, 5 tables. Code: https://github.com/showlab/EgoVLP. arXiv admin note: substantial text overlap with arXiv:2206.01670. substantial text overlap with arXiv:2207.01334

Access Paper or Ask Questions

Egocentric Video-Language Pretraining

Jun 03, 2022
Kevin Qinghong Lin, Alex Jinpeng Wang, Mattia Soldan, Michael Wray, Rui Yan, Eric Zhongcong Xu, Difei Gao, Rongcheng Tu, Wenzhe Zhao, Weijie Kong, Chengfei Cai, Hongfa Wang, Dima Damen, Bernard Ghanem, Wei Liu, Mike Zheng Shou

Figure 1 for Egocentric Video-Language Pretraining

Figure 2 for Egocentric Video-Language Pretraining

Figure 3 for Egocentric Video-Language Pretraining

Figure 4 for Egocentric Video-Language Pretraining

* Preprint. 22 pages, 13 figures, 11 tables. Code: https://github.com/showlab/EgoVLP

Access Paper or Ask Questions