Yifei Wang

Yifei Wang, Qichao Ying, Zhenxing Qian et al. · mit

Videos can be easily tampered, copied and redistributed by attackers for illegal and monetary usage. Such behaviors severely jeopardize the interest of content owners. Despite huge efforts made in digital video watermarking for copyright protection, typical distortions in video transmission including signal attacks, geometric attacks and temporal synchronization attacks can still easily erase the embedded signal. Among them, temporal synchronization attacks which include frame dropping, frame insertion and frame rate conversion is one of the most prevalent attacks. To address this issue, we present a new video watermarking based on joint Dual-Tree Cosine Wavelet Transformation (DTCWT) and Singular Value Decomposition (SVD), which is resistant to frame rate conversion. We first extract a set of candidate coefficient by applying SVD decomposition after DTCWT transform. Then, we simulate the watermark embedding by adjusting the shape of candidate coefficient. Finally, we perform group-level watermarking that includes moderate temporal redundancy to resist temporal desynchronization attacks. Extensive experimental results show that the proposed scheme is more resilient to temporal desynchronization attacks and performs better than the existing blind video watermarking schemes.

Yifei Wang, Zhengyang Geng, Feng Jiang et al.

Multi-view methods learn representations by aligning multiple views of the same image and their performance largely depends on the choice of data augmentation. In this paper, we notice that some other useful augmentations, such as image rotation, are harmful for multi-view methods because they cause a semantic shift that is too large to be aligned well. This observation motivates us to relax the exact alignment objective to better cultivate stronger augmentations. Taking image rotation as a case study, we develop a generic approach, Pretext-aware Residual Relaxation (Prelax), that relaxes the exact alignment by allowing an adaptive residual vector between different views and encoding the semantic shift through pretext-aware learning. Extensive experiments on different backbones show that our method can not only improve multi-view methods with existing augmentations, but also benefit from stronger image augmentations like rotation.

Yifei Wang, Rui Liu, Yong Chen et al.

Spectral Clustering is a popular technique to split data points into groups, especially for complex datasets. The algorithms in the Spectral Clustering family typically consist of multiple separate stages (such as similarity matrix construction, low-dimensional embedding, and K-Means clustering as post processing), which may lead to sub-optimal results because of the possible mismatch between different stages. In this paper, we propose an end-to-end single-stage learning method to clustering called Regularized Non-negative Spectral Embedding (RNSE) which extends Spectral Clustering with the adaptive learning of similarity matrix and meanwhile utilizes non-negative constraints to facilitate one-step clustering (directly from data points to clustering labels). Two well-founded methods, successive alternating projection and strategic multiplicative update, are employed to work out the quite challenging optimization problems in RNSE. Extensive experiments on both synthetic and real-world datasets demonstrate RNSE superior clustering performance to some state-of-the-art competitors.