5 papers
AutoTour: Automatic Photo Tour Guide with Smartphones and LLMs
Huatao Xu, Zihe Liu, Zilin Zeng +2
We present AutoTour, a system that enhances user exploration by automatically generating fine-grained landmark annotations and descriptive narratives for photos captured by users.…
A Robust Incomplete Multimodal Low-Rank Adaptation Approach for Emotion Recognition
Xinkui Zhao, Jinsong Shu, Yangyang Wu +6
Multimodal Emotion Recognition (MER) often encounters incomplete multimodality in practical applications due to sensor failures or privacy protection requirements. While existing m…
Efficient Model Compression for Bayesian Neural Networks
Diptarka Saha, Zihe Liu, Feng Liang
Model Compression has drawn much attention within the deep learning community recently. Compressing a dense neural network offers many advantages including lower computation cost,…
Bayesian Smoothing and Feature Selection Using variational Automatic Relevance Determination
Zihe Liu, Diptarka Saha, Feng Liang
This study introduces Variational Automatic Relevance Determination (VARD), a novel approach tailored for fitting sparse additive regression models in high-dimensional settings. VA…
NGD converges to less degenerate solutions than SGD
Moosa Saghir, N. R. Raghavendra, Zihe Liu +1
The number of free parameters, or dimension, of a model is a straightforward way to measure its complexity: a model with more parameters can encode more information. However, this…