Image super-resolution (SR) is a crucial task in computer vision that involves reconstructing
a low-resolution (LR) image into its high-resolution (HR) counterpart. Transformer-based …

Object-level out-of-distribution (OL-OOD) detection has received much attention lately due to
its importance in deploying object detection models in open-world scenarios. Recent …

Cartoon animal parsing aims to segment the body parts such as heads, arms, legs and tails
of cartoon animals. Different from previous parsing tasks, cartoon animal parsing faces new …

Cartoon parsing is an important task for cartoon-centric applications, which segments the
body parts of cartoon images. Due to the complex appearances, abstract drawing styles, and …

Video anomaly detection (VAD) is a challenging task aiming to recognize anomalies in
video frames, and existing large-scale VAD researches primarily focus on road traffic and …

Autonomous driving systems demand real-time, accurate perception to navigate complex
environments. Addressing this, we introduce the Dynamic Router Network (DyRoNet), a …

In the field of substation operation and maintenance, real-time detection and precise
segmentation of tools play an important role in maintaining the safe operation of the power …

The advancement of autonomous driving systems hinges on the ability to achieve low-
latency and high-accuracy perception. To address this critical need, this paper introduces …