Machine learning models often encounter samples that are diverged from the training
distribution. Failure to recognize an out-of-distribution (OOD) sample, and consequently …

We target the problem of zero-shot anomaly detection, in which a model is pre-trained on a
set of seen classes and expected to detect anomalies in other unseen classes at test time …

Abstract Medical Visual Question Answering (VQA) is a multimodal task to answer clinical
questions about medical images. Existing methods have achieved good performance, but …

In this article, we study the challenging few-shot fault diagnosis (FSFD) problem where
limited faulty samples are available. Metric-based meta-learning methods have been a …

Abstract Audio-Visual Question Answering (AVQA) is a sophisticated QA task, which aims at
answering textual questions over given video-audio pairs with comprehensive multimodal …

Though the sheer volume of data that is collected is immense, it is the rare categories that
are often the most important in many high-impact domains, ranging from financial fraud …

When faced with an out-of-distribution (OOD) question or image, visual question answering
(VQA) systems may provide unreliable answers. If relied on by real users or secondary …

The attention-based networks have become prevailing recently in visual question answering
(VQA) due to their high performances. However, the extensive memory consumption of …

Objective: Human–object interaction detection is to detect human–object pairs and identify
their interactions, which is of great significance to improve the perception and decision …

Generating diverse and plausible images conditioned on the given captions is an attractive
but challenging task. While many existing studies have presented impressive results, text-to …