Segment objects in a video that are mentioned in a text query
Segment objects in a video that are mentioned in a text query
End-to-End Referring Video Object Segmentation with Multimodal Transformers
arXiv paper abstract https://arxiv.org/abs/2111.14821
arXiv PDF paper https://arxiv.org/pdf/2111.14821.pdf
The referring video object segmentation task (RVOS) involves segmentation of a text-referred object instance in the frames of a given video.
... complex ... multimodal task, which combines text reasoning, video understanding, instance segmentation and tracking, existing approaches typically rely on sophisticated pipelines in order to tackle it.
... propose ... simple ... Multimodal Tracking Transformer (MTTR), models the RVOS task as a sequence prediction problem.
... MTTR is based on the realization that video and text can both be processed together effectively and elegantly by a single multimodal Transformer model.
MTTR is end-to-end trainable, free of text-related inductive bias components and requires no additional mask-refinement post-processing steps.
... MTTR significantly outperforms previous art ... impressive +5.7 and +5.0 mAP gains on the A2D-Sentences and JHMDB-Sentences datasets respectively, while processing 76 frames per second. ...
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments