A key challenge for Emotion Recognition in Conversations (ERC) is to distinguish
semantically similar emotions. Some works utilise Supervised Contrastive Learning (SCL) …

Mainstream state-of-the-art domain generalization algorithms tend to prioritize the
assumption on semantic invariance across domains. Meanwhile, the inherent intra-domain …

The efficient coding hypothesis proposes that the response properties of sensory systems
are adapted to the statistics of their inputs such that they capture maximal information about …

Recently, various methods have been introduced to address the OOD detection problem
with training outlier exposure. These methods usually count on discriminative softmax metric …

Deep learning (DL) has demonstrated remarkable performance in the classification of
hyperspectral images (HSIs) by leveraging its powerful ability to automatically learn deep …

Preserving projection learning has been widely used in feature extraction and selection for
unsupervised image classification. Generally, some related methods constructed a graph to …

This article presents a method for the automatic learning of the potentials of a stochastic
model, in particular a conditional random field (CRF), in a non-parametric fashion. The …

Our work reveals a structured shortcoming of the existing mainstream self-supervised
learning methods. Whereas self-supervised learning frameworks usually take the prevailing …

Deep learning-based visual quality inspection methods have been increasingly adopted in
product assembly process. However, the inspection for small component remains a …

Masked image modeling (MIM) has been considered as the state-of-the-art (SOTA) self-
supervised learning (SSL) technique in terms of visual pretraining. The impressive …