Concealed scene understanding (CSU) is a hot computer vision topic aiming to perceive
objects exhibiting camouflage. The current boom in terms of techniques and applications …

Unsupervised multi-object segmentation has shown impressive results on images by
utilizing powerful semantics learned from self-supervised pretraining. An additional modality …

Self-supervised methods have shown remarkable progress in learning high-level semantics
and low-level temporal correspondence. Building on these results, we take one step further …

Unsupervised video-based object-centric learning is a promising avenue to learn structured
representations from large, unlabeled video collections, but previous approaches have only …

Recent work in unsupervised multi-object segmentation shows impressive results by
predicting motion from a single image despite the inherent ambiguity in predicting motion …

This paper studies amodal image segmentation: predicting entire object segmentation
masks including both visible and invisible (occluded) parts. In previous work the amodal …

Existing approaches to unsupervised video instance segmentation typically rely on motion
estimates and experience difficulties tracking small or divergent motions. We present …

Not all camouflages are equally effective, as even a partially visible contour or a slight color
difference can make the animal stand out and break its camouflage. In this paper, we …

Motion, measured via optical flow, provides a powerful cue to discover and learn objects in
images and videos. However, compared to using appearance, it has some blind spots, such …

Automatically discovering composable abstractions from raw perceptual data is a long-
standing challenge in machine learning. Recent slot-based neural networks that learn about …