Interaction Sequences and Joint Attention

Author(s):  
Leonard Talmy
Keyword(s):  

We set forth two analytic frameworks — one pertaining to sequences of steps in a discourse AND one to common attention — to which triggers have specific relations. The framework pertaining to discourse sequences can be outlined as follows. A simplex morpheme or larger construction can be lexicalized to require either an inner or an outer sequence, which in turn can be either a single-actor or a cross-actor sequence. An interaction sequence, then, is an outer cross-actor sequence in which two collocutors alternate steps in the sequence. The steps of an interaction sequence can be either all overt or in part covert, and overt steps can be either all verbal actions or in part nonverbal actions. A step can in turn consist of a sequence of overt or covert components.

2006 ◽  
Vol 32 (4) ◽  
pp. 443-460 ◽  
Author(s):  
Adam A. Pack ◽  
Louis M. Herman

Sensors ◽  
2020 ◽  
Vol 21 (1) ◽  
pp. 54
Author(s):  
Peng Liu ◽  
Zonghua Zhang ◽  
Zhaozong Meng ◽  
Nan Gao

Depth estimation is a crucial component in many 3D vision applications. Monocular depth estimation is gaining increasing interest due to flexible use and extremely low system requirements, but inherently ill-posed and ambiguous characteristics still cause unsatisfactory estimation results. This paper proposes a new deep convolutional neural network for monocular depth estimation. The network applies joint attention feature distillation and wavelet-based loss function to recover the depth information of a scene. Two improvements were achieved, compared with previous methods. First, we combined feature distillation and joint attention mechanisms to boost feature modulation discrimination. The network extracts hierarchical features using a progressive feature distillation and refinement strategy and aggregates features using a joint attention operation. Second, we adopted a wavelet-based loss function for network training, which improves loss function effectiveness by obtaining more structural details. The experimental results on challenging indoor and outdoor benchmark datasets verified the proposed method’s superiority compared with current state-of-the-art methods.


Sign in / Sign up

Export Citation Format

Share Document