The autonomous driving community has witnessed a rapid growth in approaches that
embrace an end-to-end algorithm framework, utilizing raw sensor input to generate vehicle …

In this paper, we formally address universal object detection, which aims to detect every
scene and predict every category. The dependence on human annotations, the limited …

The heavy reliance on data is one of the major reasons that currently limit the development
of deep learning. Data quality directly dominates the effect of deep learning models, and the …

Semantic segmentation usually suffers from a long tail data distribution. Due to the
imbalanced number of samples across categories, the features of those tail classes may get …

The advent of Large Language Models (LLMs) has drastically enhanced dialogue systems.
However, comprehensively evaluating the dialogue abilities of LLMs remains a challenge …

Abstract The Facial Action Coding System is a taxonomy for fine-grained facial expression
analysis. This paper proposes a method for detecting Facial Action Units (FAU), which …

Unsupervised domain adaptation for semantic segmentation aims to assign the pixel-level
labels for unlabeled target domain by transferring knowledge from the labeled source …

The collection of large-scale datasets inevitably introduces noisy labels, leading to a
substantial degradation in the performance of deep neural networks (DNNs). Although …

How do we build a general and broad object detection system? We use all labels of all
concepts ever annotated. These labels span diverse datasets with potentially inconsistent …

Real-world data usually confronts severe class-imbalance problems, where several majority
classes have a significantly larger presence in the training set than minority classes. One …