Related papers: Anchor Diffusion for Unsupervised Video Object Seg…
Most state-of-the-art semi-supervised video object segmentation methods rely on a pixel-accurate mask of a target object provided for the first frame of a video. However, obtaining a detailed segmentation mask is expensive and…
Human behavior understanding in videos is a complex, still unsolved problem and requires to accurately model motion at both the local (pixel-wise dense prediction) and global (aggregation of motion cues) levels. Current approaches based on…
The objective of this paper is self-supervised learning of video object segmentation. We develop a unified framework which simultaneously models cross-frame dense correspondence for locally discriminative feature learning and embeds…
Unsupervised localization and segmentation are long-standing robot vision challenges that describe the critical ability for an autonomous robot to learn to decompose images into individual objects without labeled data. These tasks are…
Learning descriptive spatio-temporal object models from data is paramount for the task of semi-supervised video object segmentation. Most existing approaches mainly rely on models that estimate the segmentation mask based on a reference…
We introduce a novel robotic system for improving unseen object instance segmentation in the real world by leveraging long-term robot interaction with objects. Previous approaches either grasp or push an object and then obtain the…
The recent rise of unsupervised and self-supervised learning has dramatically reduced the dependency on labeled data, providing effective image representations for transfer to downstream vision tasks. Furthermore, recent works employed…
Unsupervised video object segmentation (VOS) aims to detect and segment the most salient object in videos. The primary techniques used in unsupervised VOS are 1) the collaboration of appearance and motion information; and 2) temporal fusion…
Recent video inpainting methods have achieved encouraging improvements by leveraging optical flow to guide pixel propagation from reference frames either in the image space or feature space. However, they would produce severe artifacts in…
Being able to learn dense semantic representations of images without supervision is an important problem in computer vision. However, despite its significance, this problem remains rather unexplored, with a few exceptions that considered…
Existing methods for video interpolation heavily rely on deep convolution neural networks, and thus suffer from their intrinsic limitations, such as content-agnostic kernel weights and restricted receptive field. To address these issues, we…
Adapter-based methods are commonly used to enhance model performance with minimal additional complexity, especially in video editing tasks that require frame-to-frame consistency. By inserting small, learnable modules into pretrained…
Unsupervised localization and segmentation are long-standing computer vision challenges that involve decomposing an image into semantically-meaningful segments without any labeled data. These tasks are particularly interesting in an…
This work addresses image restoration tasks through the lens of inverse problems using unpaired datasets. In contrast to traditional approaches -- which typically assume full knowledge of the forward model or access to paired degraded and…
Understanding temporal dynamics of video is an essential aspect of learning better video representations. Recently, transformer-based architectural designs have been extensively explored for video tasks due to their capability to capture…
Despite their irresistible success, deep learning algorithms still heavily rely on annotated data. On the other hand, unsupervised settings pose many challenges, especially about determining the right inductive bias in diverse scenarios.…
Deep learning based object detectors require thousands of diversified bounding box and class annotated examples. Though image object detectors have shown rapid progress in recent years with the release of multiple large-scale static image…
Unsupervised video object segmentation (VOS) aims to detect the most salient object in a video sequence at the pixel level. In unsupervised VOS, most state-of-the-art methods leverage motion cues obtained from optical flow maps in addition…
Moving object detection in satellite videos (SVMOD) is a challenging task due to the extremely dim and small target characteristics. Current learning-based methods extract spatio-temporal information from multi-frame dense representation…
The goal of this paper is to discover, segment, and track independently moving objects in complex visual scenes. Previous approaches have explored the use of optical flow for motion segmentation, leading to imperfect predictions due to…