Video Instance Segmentation Models

VisTR is a Transformer based video instance segmentation model. It views video instance segmentation as a direct end-to-end parallel sequence decoding/prediction problem. Given a video clip consisting of multiple image frames as input, VisTR outputs the sequence of masks for each instance in the video in order directly. At the core is a new, effective instance sequence matching and segmentation strategy, which supervises and segments instances at the sequence level as a whole. VisTR frames the instance segmentation and tracking in the same perspective of similarity learning, thus considerably simplifying the overall pipeline and is significantly different from existing approaches.

Source: End-to-End Video Instance Segmentation with Transformers


Paper Code Results Date Stars


Task Papers Share
Instance Segmentation 3 27.27%
Semantic Segmentation 3 27.27%
Video Instance Segmentation 3 27.27%
Association 1 9.09%
Video Understanding 1 9.09%


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign