English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Video object segmentation is an essential task in robot manipulation tofacilitate grasping and learning affordances. Incremental learning is importantfor robotics in unstructured environments, since the total number of objectsand their variations can be intractable. Inspired by the children learningprocess, human robot interaction (HRI) can be utilized to teach robots aboutthe world guided by humans similar to how children learn from a parent or ateacher. A human teacher can show potential objects of interest to the robot,which is able to self adapt to the teaching signal without providing manualsegmentation labels. We propose a novel teacher-student learning paradigm toteach robots about their surrounding environment. A two-stream motion andappearance "teacher" network provides pseudo-labels to adapt an appearance"student" network. The student network is able to segment the newly learnedobjects in other scenes, whether they are static or in motion. We alsointroduce a carefully designed dataset that serves the proposed HRI setup,denoted as (I)nteractive (V)ideo (O)bject (S)egmentation. Our IVOS datasetcontains teaching videos of different objects, and manipulation tasks. Unlikeprevious datasets, IVOS provides manipulation tasks sequences with segmentationannotation along with the waypoints for the robot trajectories. It alsoprovides segmentation annotation for the different transformations such astranslation, scale, planar rotation, and out-of-plane rotation. Our proposedadaptation method outperforms the state-of-the-art on DAVIS and FBMS with 6.8%and 1.2% in F-measure respectively. It improves over the baseline on IVOSdataset with 46.1% and 25.9% in mIoU.

Video Object Segmentation using Teacher-Student Adaptation in a Human Robot Interaction (HRI) Setting