Modality Compensation Network: Cross-Modal Adaptation for Action Recognition
arXiv:2001.11657
Abstract
With the prevalence of RGB-D cameras, multi-modal video data have become more available for human action recognition. One main challenge for this task lies in how to effectively leverage their complementary information. In this work, we propose a Modality Compensation Network (MCN) to explore the relationships of different modalities, and boost the representations for human action recognition. We regard RGB/optical flow videos as source modalities, skeletons as auxiliary modality. Our goal is to extract more discriminative features from source modalities, with the help of auxiliary modality. Built on deep Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM) networks, our model bridges data from source and auxiliary modalities by a modality adaptation block to achieve adaptive representation learning, that the network learns to compensate for the loss of skeletons at test time and even at training time. We explore multiple adaptation schemes to narrow the distance between source and auxiliary modal distributions from different levels, according to the alignment of source and auxiliary data in training. In addition, skeletons are only required in the training phase. Our model is able to improve the recognition performance with source data when testing. Experimental results reveal that MCN outperforms state-of-the-art approaches on four widely-used action recognition benchmarks.
Accepted by IEEE Trans. on Image Processing, 2020. Project page: http://39.96.165.147/Projects/MCN_tip2020_ssj/MCN_tip_2020_ssj.html
References in corpus (9)
- Two-Stream Convolutional Networks for Action Recognition in Videos
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Learning Transferable Features with Deep Adaptation Networks
- Recurrent Neural Network Regularization
- Domain Separation Networks
- Spatiotemporal Residual Networks for Video Action Recognition
- An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data
- Neural Paraphrase Generation with Stacked Residual LSTM Networks
- PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding