Attention meets involution in visual tracking

In visual tracking, both convolution and attention are widely employed for feature enhancement and fusion. However, convolution does not adequately model global dependencies of samples due to its operation on local neighbors, while attention gives too much attention to global dependencies and too little to local dependencies. It is intrinsically infeasible to combine both methods to integrate global and local information. However, a recently-proposed model called involution uses kernels differing in spatial extent but sharing across channels, making it possible to take advantage of both convolution and attention. We propose an attention-involution (Att-Inv) model that uses an attention mechanism to generate involution kernels to take both global and local dependencies of samples into account. To improve the performance of our tracker, we develop and implement strategies of backbone network modification, template updates, and regression of bounding box distributions. We evaluate our tracker using benchmarks such as GOT10k, LaSOT, TrackingNet and OxUvA. Experimental results show that it is competitive with state-of-the-art trackers.     

Multitone reconstruction visual cryptography based on phase periodicity

The current no-computation grayscale image visual cryptography (VC) can only achieve halftone reconstruction but cannot truly achieve multitone. To solve this problem, we propose the concept of phase periodicity of the $\lambda /2$ retarder film and calculate the optical axis angle set with phase periodicity. According to the phase periodicity, we propose a $\lambda /2$ retarder film phase periodicity visual cryptography (RPP-VC). In RPP-VC, the secret pixels are encoded as the optical axis angles of $n$ $\lambda /2$ retarder films and distributed to $n$ shares. The decoding process does not require computation. The reconstructed image has no pixel expansion and can reach up to 23 tones. The quality of the reconstructed images has been greatly improved and the evaluation indicators of perceived quality are nearly doubled compared with other grayscale image VC schemes. The experimental results verify the feasibility of RPP-VC.     

Object semantic-guided graph attention feature fusion network for Siamese visual tracking

The similarity matching between the template and the search area plays a key role in Siamese-based trackers. Most Siamese-based trackers adopt correlation operation to perform feature fusion on the template branch and search branch for similarity matching. However, the correlation operation directly uses the template feature to slide the window on the search area feature without distinguishing the discriminant part of the target and the background noise, which blurs the spatial information of the response feature. To address this issue, this work proposes a novel object semantic-guided graph attention feature fusion network that both removes background information and focuses on the discriminative part of the object. The proposed network effectively removes background noise by utilizing an adaptive template instead of the fixed-size template used by the correlation operation. The network also models the contextual semantic relations of the target and uses the resulting semantic relations to guide the feature fusion process in a part-based manner, thereby accurately highlighting the discriminative parts of the target. Therefore, the problem of blurring response feature caused by correlation operation is effectively resolved. Furthermore, we propose an object-aware prediction network to learn object-aware features for classification and regression task, which effectively improves the discriminative ability of the prediction network. Experiments on many challenging benchmarks like OTB-100, LaSOT, TColor-128, GOT-10k and VOT2019, show that our methods achieves excellent performance.