We propose a technique that propagates information forward through video data. The
method is conceptually simple and can be applied to tasks that require the propagation of …

For semantic segmentation, most existing real-time deep models trained with each frame
independently may produce inconsistent results when tested on a video sequence. A few …

We present an approach for joint inference of 3D scene structure and semantic labeling for
monocular video. Starting with monocular image stream, our framework produces a 3D …

We present an approach to long-range spatio-temporal regularization in semantic video
segmentation. Temporal regularization in video is challenging because both the camera and …

In this work, we propose a technique to convert CNN models for semantic segmentation of
static images into CNNs for video data. We describe a warping method that can be used to …

Video semantic segmentation is an essential task for the analysis and understanding of
videos. Recent efforts largely focus on supervised video segmentation by learning from fully …

In video segmentation, generating temporally consistent results across frames is as
important as achieving frame-wise accuracy. Existing methods rely either on optical flow …

Video semantic segmentation has achieved great progress under the supervision of large
amounts of labelled training data. However, domain adaptive video segmentation, which …

Semantic segmentation of aerial videos has been extensively used for decision making in
monitoring environmental changes, urban planning, and disaster management. The …

Unsupervised domain adaptation (UDA) aims to transfer knowledge in previous and related
labeled datasets (sources) to a new unlabeled dataset (target). Despite the impressive …