Local Temporal Bilinear Pooling for Fine-grained Action Parsing
This work addresses the problem of subtle and precise action analysis in applications like daily activity understanding and surgical robotics, representing an incremental improvement through a novel method for a known bottleneck.
The paper tackles fine-grained temporal action parsing by proposing a learnable bilinear pooling operation within a temporal convolutional encoder-decoder network, achieving superior performance over state-of-the-art methods on various datasets.
Fine-grained temporal action parsing is important in many applications, such as daily activity understanding, human motion analysis, surgical robotics and others requiring subtle and precise operations in a long-term period. In this paper we propose a novel bilinear pooling operation, which is used in intermediate layers of a temporal convolutional encoder-decoder net. In contrast to other work, our proposed bilinear pooling is learnable and hence can capture more complex local statistics than the conventional counterpart. In addition, we introduce exact lower-dimension representations of our bilinear forms, so that the dimensionality is reduced with neither information loss nor extra computation. We perform intensive experiments to quantitatively analyze our model and show the superior performances to other state-of-the-art work on various datasets.