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

We propose MinVIS, a minimal video instance segmentation (VIS) framework thatachieves state-of-the-art VIS performance with neither video-basedarchitectures nor training procedures. By only training a query-based imageinstance segmentation model, MinVIS outperforms the previous best result on thechallenging Occluded VIS dataset by over 10% AP. Since MinVIS treats frames intraining videos as independent images, we can drastically sub-sample theannotated frames in training videos without any modifications. With only 1% oflabeled frames, MinVIS outperforms or is comparable to fully-supervisedstate-of-the-art approaches on YouTube-VIS 2019/2021. Our key observation isthat queries trained to be discriminative between intra-frame object instancesare temporally consistent and can be used to track instances without anymanually designed heuristics. MinVIS thus has the following inference pipeline:we first apply the trained query-based image instance segmentation to videoframes independently. The segmented instances are then tracked by bipartitematching of the corresponding queries. This inference is done in an onlinefashion and does not need to process the whole video at once. MinVIS thus hasthe practical advantages of reducing both the labeling costs and the memoryrequirements, while not sacrificing the VIS performance. Code is available at:https://github.com/NVlabs/MinVIS

MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training