MARS: Motion-Augmented RGB Stream for Action Recognition

Most state-of-the-art methods for action recognition consist of a two-stream architecture with 3D convolutions: an appearance stream for RGB frames and a motion stream for optical flow frames. Although combining flow with RGB improves the performance, the cost of computing accurate optical flow is high, and increases action recognition latency. This limits the usage of two-stream approaches in real-world applications requiring low latency. In this paper, we introduce two learning approaches to train a standard 3D CNN, operating on RGB frames, that mimics the motion stream, and as a result avoids flow computation at test time. First, by minimizing a feature-based loss compared to the Flow stream, we show that the network reproduces the motion stream with high fidelity. Second, to leverage both appearance and motion information effectively, we train with a linear combination of the feature-based loss and the standard cross-entropy loss for action recognition. We denote the stream trained using this combined loss as Motion-Augmented RGB Stream (MARS). As a single stream, MARS performs better than RGB or Flow alone, for instance with 72.7% accuracy on Kinetics compared to 72.0% and 65.6% with RGB and Flow streams respectively.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Benchmark
Action Recognition HMDB-51 MARS+RGB+FLow (64 frames, Kinetics pretrained) Average accuracy of 3 splits 80.9 # 15
Action Classification Kinetics-400 MARS+RGB+Flow (16 frames) Acc@1 68.9 # 129
Action Classification Kinetics-400 MARS+RGB+Flow (64 frames) Acc@1 74.9 # 106
Action Classification MiniKinetics MARS+RGB+Flow (16 frames) Top-1 Accuracy 73.5 # 1
Action Recognition Something-Something V1 MARS+RGB+Flow (16 frames, Kinetics pretrained) Top 1 Accuracy 40.4 # 56
Action Recognition Something-Something V1 MARS+RGB+Flow (64 frames, Kinetics pretrained) Top 1 Accuracy 53.0 # 22
Action Recognition UCF101 MARS+RGB+Flow (16 frames) 3-fold Accuracy 95.8 # 33
Action Recognition UCF101 MARS+RGB+Flow (64 frames, Kinetics pretrained) 3-fold Accuracy 97.8 # 6

Methods


No methods listed for this paper. Add relevant methods here