Action segmentation with joint self-supervised temporal domain adaptation
Despite the recent progress of fully-supervised action segmentation techniques, the
performance is still not fully satisfactory. One main challenge is the problem of …
performance is still not fully satisfactory. One main challenge is the problem of …
Unsupervised object detection with scene-adaptive concept learning
Object detection is one of the hottest research directions in computer vision, has already
made impressive progress in academia, and has many valuable applications in the industry …
made impressive progress in academia, and has many valuable applications in the industry …
Exploring Spatial-Temporal Instance Relationships in an Intermediate Domain for Image-to-Video Object Detection
Image-to-video object detection leverages annotated images to help detect objects in
unannotated videos, so as to break the heavy dependency on the expensive annotation of …
unannotated videos, so as to break the heavy dependency on the expensive annotation of …