Expert systems are being extensively used to make critical decisions involving emotional
analysis in affective computing. The evolution of deep learning algorithms has improved the …

Tensor network (TN) decomposition is a promising framework to represent extremely high-
dimensional problems with few parameters. However, it is challenging to search the (near-) …

Most multimodal learning methods assume that all modalities are always available in data.
However, in real-world applications, the assumption is often violated due to privacy …

As an inevitable phenomenon in real-world applications, data imperfection has emerged as
one of the most critical challenges for multimodal sentiment analysis. However, existing …

Improving model robustness against potential modality noise, as an essential step for
adapting multimodal models to real-world applications, has received increasing attention …

Tensor-power (TP) recurrent model is a family of non-linear dynamical systems, of which the
recurrence relation consists of a p-fold (aka, degree-p) tensor product. Despite such the …

As a vital aspect of affective computing, Multimodal Emotion Recognition has been an active
research area in the multimedia community. Despite recent progress, this field still confronts …

The tensor recurrent model is a family of nonlinear dynamical systems, of which the
recurrence relation consists of a-fold (called degree-) tensor product. Despite such models …

Improving the robustness of models against feature noise has emerged as one of the most
crucial research topics in the field of multimodal sentiment analysis. Recent studies assume …

We present OpenVNA, an open-source framework designed for analyzing the behavior of
multimodal language understanding systems under noisy conditions. OpenVNA serves as …