-
1
A new data transmission paradigm for visual analysis in edge-cloud collaboration
Published 2021“…To enable better balance among computing load, bandwidth usage and generalization ability, I propose a new paradigm of transmitting intermediate deep learning features instead of visual signals or ultimately utilized features, which inspires research and standardization of compression techniques for intermediate deep learning features. …”
Get full text
Thesis-Doctor of Philosophy -
2
Representation learning for recommender systems
Published 2021“…Our proposed approach hinges upon the key intuition that the decision making process (in groups) is generally dynamic, i.e., a user's decision is highly dependent on the other group members. …”
Get full text
Thesis-Doctor of Philosophy -
3
System architecture and technology for real-time heterogeneous co-editing
Published 2022“…This state-based operation derivation approach is particularly suitable for supporting heterogeneous co-editing as it can derive operations in a generalized way, i.e., one common set of state-based operation derivation algorithms can be used for all editors (regardless of their editing capabilities and interaction styles). …”
Get full text
Thesis-Doctor of Philosophy