Zejia Weng

Orcid: 0000-0001-9706-6484

According to our database1, Zejia Weng authored at least 12 papers between 2020 and 2024.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
HCMS: Hierarchical and Conditional Modality Selection for Efficient Video Recognition.
ACM Trans. Multim. Comput. Commun. Appl., February, 2024

2023
Cross-Domain Contrastive Learning for Unsupervised Domain Adaptation.
IEEE Trans. Multim., 2023

To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuning.
CoRR, 2023

Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and Data.
CoRR, 2023

BMB: Balanced Memory Bank for Imbalanced Semi-supervised Learning.
CoRR, 2023

Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization.
CoRR, 2023

Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization.
Proceedings of the International Conference on Machine Learning, 2023

2022
Semi-supervised Vision Transformers.
Proceedings of the Computer Vision - ECCV 2022, 2022

2021
HMS: Hierarchical Modality Selection for Efficient Video Recognition.
CoRR, 2021

A Multimodal Framework for Video Ads Understanding.
Proceedings of the MM '21: ACM Multimedia Conference, Virtual Event, China, October 20, 2021

VideoLT: Large-scale Long-tailed Video Recognition.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

2020
Imbalanced Gradients: A New Cause of Overestimated Adversarial Robustness.
CoRR, 2020


  Loading...