-
1
User-specific recommender systems: from data to model
Published 2022“…In the era of big data, recommender systems are widely adopted by online platforms (e.g., Amazon and YouTube), so as to provide target users with meaningful recommendation and alleviate the problem of information overload. …”
Get full text
Thesis-Doctor of Philosophy -
2
Design and evaluation of a video retrieval environment for exploratory searches in a learning context
Published 2020“…Public video repositories on the Internet, such as YouTube, Vimeo, and others serve as good resources for self-directed learning (SDL). …”
Get full text
Thesis-Doctor of Philosophy -
3
Leveraging deep learning for visual understanding of videos
Published 2024“…The work proposed in this thesis explores the potential of self-supervised learning for video object segmentation, aiming to harness freely available internet data such as YouTube videos for model training. Different from existing self-supervised learning approaches for video object segmentation that model pixel-to-pixel correspondence, this research shifts the focus towards modeling superpixel-to-superpixel correspondence. …”
Get full text
Thesis-Doctor of Philosophy -
4
Towards unbiased visual language reasoning and consistent segmentation
Published 2023“…Not surprisingly, the proposed method outperforms the previous state-of-the-art methods on two popular multi-object benchmarks, YouTube-VOS and DAVIS 2017, and one single-object benchmark, DAVIS 2016. …”
Get full text
Thesis-Doctor of Philosophy