Code up both a learning free and a learned convolutional aggregation followed by one of the fixed pooling methods (max by default). The learning-free convolutional aggregation is just performing an element-wise temporal smoothing (with something like a Gaussian or triangular kernel, whose bandwidth is a free hyper-parameter) -- then followed by pooling. The learned convolutional aggregation has a fully-learned convolutional layer (all-to-all, not element-wise) -- followed by pooling.
Test the learning-free variant on the single-frame emotion classifier outputs.
Code up both a learning free and a learned convolutional aggregation followed by one of the fixed pooling methods (max by default). The learning-free convolutional aggregation is just performing an element-wise temporal smoothing (with something like a Gaussian or triangular kernel, whose bandwidth is a free hyper-parameter) -- then followed by pooling. The learned convolutional aggregation has a fully-learned convolutional layer (all-to-all, not element-wise) -- followed by pooling.
Test the learning-free variant on the single-frame emotion classifier outputs.