Abstract Visual Question Answering (VQA) models often perform poorly on out-of-distribution
data and struggle on domain generalization. Due to the multi-modal nature of this task …

Despite rapid progress in Visual question answering (\textit {VQA}), existing datasets and
models mainly focus on testing reasoning in 2D. However, it is important that VQA models …

In this paper we make the first attempt at achieving the cross-modal (ie image-to-events)
adaptation for event-based object recognition without accessing any labeled source image …

Segmenting object parts such as cup handles and animal bodies is important in many real-
world applications but requires more annotation effort. The largest dataset nowadays …

Part-aware panoptic segmentation (PPS) requires (a) that each foreground object and
background region in an image is segmented and classified and (b) that all parts within …

To effectively interrogate UAV-based images for detecting objects of interest, such as
humans, it is essential to acquire large-scale UAV-based datasets that include human …

An important and unsolved problem in computer vision is to ensure that the algorithms are
robust to changes in image domains. We address this problem in the scenario where we …

Fine-grained visual parsing, including fine-grained part segmentation and fine-grained
object recognition, has attracted considerable critical attention due to its importance in many …

Three-dimensional object modeling is necessary for developing virtual and augmented
reality applications. Traditionally, application engineers must manually use art software to …

The study of complex human interactions and group activities has become a focal point in
human-centric computer vision. However progress in related tasks is often hindered by the …