This paper presents ClusterFormer, a universal vision model that is based on the Clustering
paradigm with TransFormer. It comprises two novel designs: 1) recurrent cross-attention …

Abstract Visual Place Recognition is a task that aims to predict the place of an image (called
query) based solely on its visual features. This is typically done through image retrieval …

Video objection detection is a challenging task because isolated video frames may
encounter appearance deterioration, which introduces great confusion for detection. One of …

Prevalent state-of-the-art instance segmentation methods fall into a query-based scheme, in
which instance masks are derived by querying the image feature using a set of instance …

We present CLUSTSEG, a general, transformer-based framework that tackles different
image segmentation tasks (ie, superpixel, semantic, instance, and panoptic) through a …

Deep learning has substantially boosted the performance of Monocular Depth Estimation
(MDE), a critical component in fully vision-based autonomous driving (AD) systems (eg …

Abstract Deep Supervised Salient Object Detection (SSOD) excessively relies on large-
scale annotated pixel-level labels which consume intensive labour acquiring high quality …

Autonomous vehicles integrate complex software stacks for realizing the necessary iterative
perception, planning, and action operations. One of the foundational layers of such stacks is …

Visual Place Recognition (VPR) is often characterized as being able to recognize the same
place despite significant changes in appearance and viewpoint. VPR is a key component of …

Instance segmentation in videos, which aims to segment and track multiple objects in video
frames, has garnered a flurry of research attention in recent years. In this paper, we present …