We present an unsupervised representation learning approach using videos without semantic labels. We leverage the temporal coherence as a supervisory signal by formulating representation learning as a sequence sorting task. We take temporally shuffled frames (i.e., in non-chronological order) as inputs and train a convolutional neural network to sort the shuffled sequences. Similar to comparison-based sorting algorithms, we propose to extract features from all frame pairs and aggregate them to predict the correct order. As sorting shuffled image sequence requires an understanding of the statistical temporal structure of images, training with such a proxy task allows us to learn rich and generalizable visual representation. We validate the effectiveness of the learned representation using our method as pre-training on high-level recognition problems. The experimental results show that our method compares favorably against state-of-the-art methods on action recognition, image classification, and object detection tasks.
|Title of host publication||Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||10|
|Publication status||Published - 2017 Dec 22|
|Event||16th IEEE International Conference on Computer Vision, ICCV 2017 - Venice, Italy|
Duration: 2017 Oct 22 → 2017 Oct 29
|Name||Proceedings of the IEEE International Conference on Computer Vision|
|Other||16th IEEE International Conference on Computer Vision, ICCV 2017|
|Period||17/10/22 → 17/10/29|
Bibliographical notePublisher Copyright:
© 2017 IEEE.
All Science Journal Classification (ASJC) codes
- Computer Vision and Pattern Recognition