Jieying Zheng

Face sketch synthesis for photos is an applied research topic and it is critical for criminal investigation. However, sketch synthesis remains some challenges because of the blur and artifacts in the generated face sketches. To mitigate these problems in face sketch synthesis, we propose a fast Generative Adversarial Network with fast Multi-scale feature channel Attention, namely MAGAN. In the generator network, multi-scale features are extracted by proposed multi-scale feature extraction to produce detailed sketches. Then, a channel attention mechanism is applied to emphasize the significance of important feature channels, further enhancing the synthesized sketches. Besides, the loss of patch-wise high-layer features from the VGG-19 network is applied to supervise the generator to synthesize more realistic sketches. To accelerate the training process, the features from the pooling layers are adopted to calculate the pseudo sketch feature loss. The experimental results demonstrate that our MAGAN can achieve better performance in both visual evaluations and quantitative evaluations (in terms of feature similarity and learned perceptual image patch similarity), compared with the state-of-the-art methods.

Recently, person re-identification has become one of the research hotspots in the field of computer vision and has received extensive attention in the academic community. Inspired by the part-based research of image ReID, this paper presents a novel feature learning and extraction framework for video-based person re-identification, namely, the extended global-local representation learning network (E-GLRN). Given a video sequence of a pedestrian, the holistic and local features are simultaneously extracted using the E-GLRN network. Specifically, for the global feature learning, we adopt the channel attention convolutional neural network (CNN) and the bidirectional long short-term memory (Bi-LSTM) networks, which are responsible for introducing a CNN-LSTM module to learn the features of consecutive frames. The local feature learning module relies on the key local information extraction, which is based on the Bi-LSTM networks. In order to obtain the local feature more effectively, our work defines a concept of “the main image group” by selecting three representative frames. The local feature representation of a video is obtained by exploiting the spatial contextual and appearance information of this group. The local and global features extracted in this paper are complementary and further combined into a discriminative and robust feature representation of the video sequence. Extensive experiments are conducted on three video-based ReID datasets, including the iLIDS-VID, PRID2011 and MARS datasets. The experimental results demonstrate that the proposed method outperforms state-of-the-art video-based re-identification approaches.

This paper proposes a learning-based image interpolation method based on weighted direct nonlinear regression. It attempts to learn the nonlinear relationship between the low-resolution patches and their corresponding high-resolution patches by using an external database of natural images. In the training phase, without being initialized to the same size as the high-resolution patches using bicubic interpolation, low-resolution patches are directly used for training, which will reduce the number of parameters. Dictionary learning combined with nearest neighbor searching based on the normalized correlation coefficient in the entire training set is proposed as a soft classification method. Afterward, a single hidden-layer feed-forward network with random input weights is adopted to learn the direct nonlinear mapping for the regression in each class. In the interpolation phase, the strategy of weighting multiple estimations is applied to enhance the interpolation performance. Furthermore, a refinement process is proposed to improve the interpolation performance with sharper edges and richer details. Extensive experimental results demonstrate that our proposed method is not only effective and efficient but also outperforms many state-of-the-art methods.