Abstract Dense Event Captioning (DEC) aims to jointly localize and describe multiple events
of interest in untrimmed videos, which is an advancement of the conventional video …

Deep learning models have achieved great success in many fields, yet they are vulnerable
to adversarial examples. This paper follows a causal perspective to look into the adversarial …

Class imbalance is a common challenge in real-world recognition tasks, where the majority
of classes have few samples, also known as tail classes. We address this challenge with the …

Real-world data often exhibits class-imbalanced distributions, where a few classes (aka
majority classes) occupy most instances and lots of classes (aka minority classes) have few …

Vision-language models (VLMs) that use contrastive language-image pre-training have
shown promising zero-shot classification performance. However, their performance on …

The real-world data tends to be heavily imbalanced and severely skew the data-driven deep
neural networks, which makes Long-Tailed Recognition (LTR) a massive challenging task …

Deep neural networks (DNNs) are recently shown to be vulnerable to backdoor attacks,
where attackers embed hidden backdoors in the DNN model by injecting a few poisoned …

Vanilla models for object detection and instance segmentation suffer from the heavy bias
toward detecting frequent objects in the long-tailed setting. Existing methods address this …

Foundation models like CLIP allow zero-shot transfer on various tasks without additional
training data. Yet, the zero-shot performance is less competitive than a fully supervised one …

Despite the previous success of object analysis, detecting and segmenting a large number
of object categories with a long-tailed data distribution remains a challenging problem and is …