Yunhua Zhang

I am a PhD candidate at University of Amsterdam (UvA), advised by Prof. Cees Snoek and Dr. Hazel Doughty.

Email  /  Google Scholar  /  Github  /  ELLIS PhD Program

Awesome-Video-Datasets

My research areas are computer vision, video understanding, multimodal learning and foundation models.

• 2024/04. Incoming research scientist intern at Meta (Menlo Park).
• 2022/10. Happy to be an outstanding reviewer for ECCV 2022.
• 2022/09-2023/01. Did an internship at Meta Reality Labs as a research scientist intern in Redmond, WA.

Low-resource settings are well-established in natural language processing, where many languages lack sufficient data for machine learning at scale. However, low-resource problems are under-explored in computer vision. In this paper, we strive to address this gap and explore the challenges of low-resource image tasks with vision foundation models.

Multimodal learning assumes all modality combinations of interest are available during training to learn cross-modal correspondences. In this paper, we challenge this modality-complete assumption for multimodal learning and instead strive for generalization to unseen modality combinations during inference.

State-of-the-art activity recognizers are effective during the day, but not trustworthy in the dark. The main causes are the distribution shift from the lower color contrast as well as the limited availability of labeled dark videos. Our goal is to recognize activities in the dark as well as in the day.

This paper strives for activity recognition under domain shift, for example caused by change of scenery or camera viewpoint. Different from vision-focused works we leverage activity sounds for domain adaptation as they have less variance across domains and can reliably indicate which activities are not happening.

We incorporate for the first time the corresponding sound into the repetition counting process. This benefits accuracy in challenging vision conditions such as occlusion, dramatic camera view changes, low resolution, etc.

This paper proposes a new visual tracking algorithm, which leverages the merits of both template matching approaches and classification models for long-term object detection and tracking.

In this work, we propose a novel offline-trained Meta-Updater to address an important but unsolved problem: Is the tracker ready for updating in the current frame?

In this paper, we propose a local structure learning method, which simultaneously considers the local patterns of the target and their structural relationships for more accurate target tracking.

This website uses the template provided by Jon Barron.