Article

Mutual Context Network for Jointly Estimating Egocentric Gaze and Actions
In this work, we address two coupled tasks of gaze prediction and action recognition in egocentric videos by exploring their mutual …
PDF 引用
Understanding hand-object manipulation by modeling the contextual relationship between actions, grasp types and object attributes
PDF 引用
Hierarchical Gaussian Descriptors with Application to Person Re-Identification
PDF 引用
Seeing with Humans: Gaze-Assisted Neural Image Captioning
PDF 引用