Xin Gu

Affiliations:

ByteDance Inc., Mountain View, CA, USA
University of Chinese Academy of Sciences (UCAS), China
Chinese Academy of Sciences (CAS), Institute of Software, China

According to our database¹, Xin Gu authored at least 9 papers between 2022 and 2025.

Collaborative distances:

Dijkstra number² of five.
Erdős number³ of five.

Timeline

Legend:

Book

In proceedings

Article

PhD thesis

Dataset

Other

Links

On csauthors.net:

Bibliography

2025

OmniSTVG: Toward Spatio-Temporal Omni-Object Video Grounding.

[BibT_eX]

[DOI]

CoRR, March, 2025

Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Multi-Reward as Condition for Instruction-based Image Editing.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Local Compressed Video Stream Learning for Generic Event Boundary Detection.

[BibT_eX]

[DOI]

Int. J. Comput. Vis., April, 2024

Edit3K: Universal Representation Learning for Video Editing Components.

[BibT_eX]

[DOI]

CoRR, 2024

Context-Guided Spatio-Temporal Video Grounding.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023

Accurate and Fast Compressed Video Captioning.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Text with Knowledge Graph Augmented Transformer for Video Captioning.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

Dual-Stream Transformer for Generic Event Boundary Captioning.

[BibT_eX]

[DOI]

CoRR, 2022

Xin Gu

Timeline

Legend:

Links

On csauthors.net:

Bibliography

Loading...