University of Oulu

M. Tavakolian, H. R. Tavakoli and A. Hadid, "AWSD: Adaptive Weighted Spatiotemporal Distillation for Video Representation," 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), 2019, pp. 8019-8028.

AWSD : adaptive weighted spatiotemporal distillation for video representation

Saved in:
Author: Tavakolian, Mohammad1; Tavakoli, Hamed R.2,3; Hadid, Abdenour4
Organizations: 1University of Oulu
2Aalto University
3Nokia Technologies
4Univesity of Oulu
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 4.9 MB)
Persistent link:
Language: English
Published: IEEE Computer Society, 2020
Publish Date: 2020-03-25


We propose an Adaptive Weighted Spatiotemporal Distillation (AWSD) technique for video representation by encoding the appearance and dynamics of the videos into a single RGB image map. This is obtained by adaptively dividing the videos into small segments and comparing two consecutive segments. This allows using pre-trained models on still images for video classification while successfully capturing the spatiotemporal variations in the videos. The adaptive segment selection enables effective encoding of the essential discriminative information of untrimmed videos. Based on Gaussian Scale Mixture, we compute the weights by extracting the mutual information between two consecutive segments. Unlike pooling-based methods, our AWSD gives more importance to the frames that characterize actions or events thanks to its adaptive segment length selection. We conducted extensive experimental analysis to evaluate the effectiveness of our proposed method and compared our results against those of recent state-of-the-art methods on four benchmark datatsets, including UCF101, HMDB51, ActivityNet v1.3, and Maryland. The obtained results on these benchmark datatsets showed that our method significantly outperforms earlier works and sets the new state-of-the-art performance in video classification. Code is available at the project webpage:

see all

Series: IEEE International Conference on Computer Vision
ISSN: 1550-5499
ISSN-E: 2380-7504
ISSN-L: 1550-5499
ISBN: 978-1-7281-4803-8
ISBN Print: 978-1-7281-4804-5
Pages: 8019 - 8028
DOI: 10.1109/ICCV.2019.00811
Host publication: 2019 IEEE International Conference on Computer Vision (ICCV) : 27th October- 2nd Novenber 2019, Seoul, Korea
Conference: IEEE International Conference on Computer Vision
Type of Publication: A4 Article in conference proceedings
Field of Science: 113 Computer and information sciences
Copyright information: © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.