Local Temporal Bilinear Pooling for Fine-grained Action Parsing

12/05/2018
by   Yan Zhang, et al.
0

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.

READ FULL TEXT
research
07/26/2018

Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition

Fine-grained visual recognition is challenging because it highly relies ...
research
04/07/2019

Compare More Nuanced:Pairwise Alignment Bilinear Network For Few-shot Fine-grained Learning

The recognition ability of human beings is developed in a progressive wa...
research
06/03/2019

Low-rank Random Tensor for Bilinear Pooling

Bilinear pooling is capable of extracting high-order information from da...
research
12/18/2020

Temporal Bilinear Encoding Network of Audio-Visual Features at Low Sampling Rates

Current deep learning based video classification architectures are typic...
research
11/04/2017

Attentional Pooling for Action Recognition

We introduce a simple yet surprisingly powerful model to incorporate att...
research
11/25/2018

Temporal Bilinear Networks for Video Action Recognition

Temporal modeling in videos is a fundamental yet challenging problem in ...
research
02/20/2018

MoNet: Moments Embedding Network

Bilinear pooling has been recently proposed as a feature encoding layer,...

Please sign up or login with your details

Forgot password? Click here to reset