چکیده مقاله
In this paper, we examined different ways for classifying videos with two dimensional Convolutional Neural Networks CNNs By calculating energy of optical flow between frames, we found that classification with CNNs by feeding frames with high energy of optical flow can outperform results in comparison with feeding consecutive frames with highly similar content It is demontrated that the energy of optical flow has straight relationship with classification accuracy
کلیدواژهها
نویسندگان
Ali Javidani
Department of Computer Science and Engineering Shahid Beheshti University Tehran, Iran
Ahmad Mahmoudi-Aznaveh
Cyberspace Research Center Shahid Beheshti University Tehran, Iran
Ehsan Javidani
Hamedan University of Technology, Hamedan, Iran
شیوه ارجاع
Javidani, Ali and Mahmoudi-Aznaveh, Ahmad and Javidani, Ehsan,1396,Video Classification with Multi-Channel Convolutional Neural Networks,Fifth International Conference on Electrical and Computer Engineering with Emphasis on Indigenous Knowledge,Tehran
ارائهشده در
مجموعه مقالات پنجمین کنفرانس بین المللی مهندسی برق و کامپیوتر با تاکید بر دانش بومی19 بهمن 1396 · تهران