Ensemble Convolution Neural Network for Robust Video Emotion Recognition Using Deep Semantics

Algorithm 3

Occlusion detection from patched image.

	Input: Keyframes
	Output: Representation of occluded face
	Input the extracted keyframe as a face image
	Generate a feature map (FM) from each keyframe
	Return 24 local patches (, … )
	For each local patch
	Decomposes the feature map into 24 subfeature-maps (… )
	Encode a weighted vector (wv) of local feature (lf) by a PG-Unit
	PG-Unit computes the weight by an attention net based on its obstructed-ness
	Concatenate the weighted local features
	Return the representation of the occluded face.
	End For