1-3hit |
Yinan LIU Qingbo WU Liangzhi TANG Linfeng XU
In this paper, we propose a novel self-supervised learning of video representation which is capable to anticipate the video category by only reading its short clip. The key idea is that we employ the Siamese convolutional network to model the self-supervised feature learning as two different image matching problems. By using frame encoding, the proposed video representation could be extracted from different temporal scales. We refine the training process via a motion-based temporal segmentation strategy. The learned representations for videos can be not only applied to action anticipation, but also to action recognition. We verify the effectiveness of the proposed approach on both action anticipation and action recognition using two datasets namely UCF101 and HMDB51. The experiments show that we can achieve comparable results with the state-of-the-art self-supervised learning methods on both tasks.
Sangwook LEE Ji Eun SONG Wan Yeon LEE Young Woong KO Heejo LEE
For digital forensic investigations, the proposed scheme verifies the integrity of video contents in legacy surveillance camera systems with no built-in integrity protection. The scheme exploits video frames remaining in slack space of storage media, instead of timestamp information vulnerable to tampering. The scheme is applied to integrity verification of video contents formatted with AVI or MP4 files in automobile blackboxes.
Miki HASEYAMA Makoto TAKIZAWA Takashi YAMAMOTO
In this paper, a new video frame interpolation method based on image morphing for frame rate up-conversion is proposed. In this method, image features are extracted by Scale-Invariant Feature Transform in each frame, and their correspondence in two contiguous frames is then computed separately in foreground and background regions. By using the above two functions, the proposed method accurately generates interpolation frames and thus achieves frame rate up-conversion.