Motion representation plays a vital role in human action recognition in videos. In this study, we introduce a novel compact motion representation for video action recognition, named Optical Flow guided Feature (OFF), which enables the network to distill temporal information through a fast and robust approach. The OFF is derived from the definition of optical flow and is orthogonal to the optical flow. The derivation also provides theoretical support for using the difference between two frames. By directly calculating pixel-wise spatio-temporal gradients of the deep feature maps, the OFF could be embedded in any existing CNN based video action recognition framework with only a slight additional cost. It enables the CNN to extract spatiotemporal information, especially the temporal information between frames simultaneously. This simple but powerful idea is validated by experimental results. The network with OFF fed only by RGB inputs achieves a competitive accuracy of 93.3% on UCF-101, which is comparable with the result obtained by two streams (RGB and optical flow), but is 15 times faster in speed. Experimental results also show that OFF is complementary to other motion modalities such as optical flow. When the proposed method is plugged into the state-of-the-art video action recognition framework, it has 96.0% and 74.2% accuracy on UCF-101 and HMDB-51 respectively. The code for this project is available at: https://github.com/kevin-ssy/Optical-Flow-Guided-Feature
Mg-3wt%Al anodes with Sn, Ga and In were prepared by melting and heat-treatment in electric resistance furnace. The electrochemical discharge behavior of these anodes in 3.5wt% NaCl solutions was studied by potentiodynamic polarization and electrochemical impedance spectroscopy (EIS). The microstructures and the corroded surfaces of the anodes were investigated by scanning electron microscopy (SEM) and energy dispersive spectrometer (EDS). Finally, Mg-air batteries based on Mg-3Al-1Sn (AS31), Mg-3Al-1Ga (AG31), Mg-3Al-1In (AI31) alloys were prepared and battery properties were studied by constant current discharge test. Mg-3Al (A3) and Mg-3Al-1Zn (AZ31) were also prepared to be used for contrast test. The results show AI31 behaves good comprehensive properties, the battery based on AI31 anode possesses the highest capacity density (1382 mAhg−1) and power density (18.5 mWcm−2). Compared with A3 and AZ31, AS31 and AG31 show higher corrosion resistance. In addition, The paper also researches on the modification mechanism of Ga, In and Sn on Mg-3Al.
Where a licence is displayed above, please note the terms and conditions of the licence govern your use of this document. When citing, please reference the published version. Take down policy While the University of Birmingham exercises care and attention in making items available there are rare occasions when an item has been uploaded in error or has been deemed to be commercially or otherwise sensitive.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.