Image emotion classification (IEC) aims to extract the abstract emotions evoked in images. Recently, language-supervised methods such as contrastive language-image pretraining (CLIP) have demonstrated superior performance in image understanding. However, the underexplored task of IEC presents three major challenges: a tremendous training objective gap between pretraining and IEC, shared suboptimal prompts, and invariant prompts for all instances. In this study, we propose a general framework that effectively exploits the language-supervised CLIP method for the IEC task. First, a prompt-tuning method that mimics the pretraining objective of CLIP is introduced, to exploit the rich image and text semantics associated with CLIP. Subsequently, instance-specific prompts are automatically composed, conditioning them on the categories and image content of instances, diversifying the prompts, and thus avoiding suboptimal problems. Evaluations on six widely used affective datasets show that the proposed method significantly outperforms state-of-the-art methods (up to 9.29% accuracy gain on the EmotionROI dataset) on IEC tasks with only a few trained parameters. The code is publicly available at https://github.com/dsn0w/PT-DPC/for research purposes.

Free viewpoint video (FVV) has received considerable attention owing to its widespread applications in several areas such as immersive entertainment, remote surveillance and distanced education. Since FVV images are synthesized via a depth image-based rendering (DIBR) procedure in the “blind” environment (without reference images), a real-time and reliable blind quality assessment metric is urgently required. However, the existing image quality assessment metrics are insensitive to the geometric distortions engendered by DIBR. In this research, a novel blind method of DIBR-synthesized images is proposed based on measuring geometric distortion, global sharpness and image complexity. First, a DIBR-synthesized image is decomposed into wavelet subbands by using discrete wavelet transform. Then, the Canny operator is employed to detect the edges of the binarized low-frequency subband and high-frequency subbands. The edge similarities between the binarized low-frequency subband and high-frequency subbands are further computed to quantify geometric distortions in DIBR-synthesized images. Second, the log-energies of wavelet subbands are calculated to evaluate global sharpness in DIBR-synthesized images. Third, a hybrid filter combining the autoregressive and bilateral filters is adopted to compute image complexity. Finally, the overall quality score is derived to normalize geometric distortion and global sharpness by the image complexity. Experiments show that our proposed quality method is superior to the competing reference-free state-of-the-art DIBR-synthesized image quality models.

Purpose: In some three-dimensional (3D) printing application scenarios, e.g., model manufacture, it is necessary to print large-sized objects. However, it is impossible to implement large-size 3D printing using a single projector in digital light processing (DLP)-based mask projection 3D printing because of the limitations of the digital micromirror device chips. Design/methodology/approach: A multi-projector DLP with energy homogenization (EHMP-DLP) scheme is proposed for large-size 3D printing. First, a large-area printing plane is established by tiling multiple projectors. Second, the projector set’s tiling pattern is obtained automatically, and the maximum printable plane is determined. Third, the energy is homogenized across the entire printable plane by adjusting gray levels of the images input into the projectors. Finally, slices are automatically segmented based on the tiling pattern of the projector set, and the gray levels of these slices are reassigned based on the images of the corresponding projectors. Findings: Large-area high-intensity projection for mask projection 3D printing can be performed by tiling multiple DLP projectors. The tiled projector output energies can be homogenized by adjusting the images of the projectors. Uniform ultraviolet energy is important for high-quality printing. Practical implications: A prototype device is constructed using two projectors. The printable area becomes 140 × 210 mm from the original 140 × 110 mm. Originality/value: The proposed EHMP-DLP scheme enables 3D printing of large-size objects with linearly increasing printing times and high printing precision. A device was established using two projectors to practice the scheme and can easily be extended to larger sizes by using more projectors.

Human group activity recognition (GAR) has attracted significant attention from computer vision researchers due to its wide practical applications in security surveillance, social role understanding and sports video analysis. In this paper, we give a comprehensive overview of the advances in group activity recognition in videos during the past 20 years. First, we provide a summary and comparison of 11 GAR video datasets in this field. Second, we survey the group activity recognition methods, including those based on handcrafted features and those based on deep learning networks. For better understanding of the pros and cons of these methods, we compare various models from the past to the present. Finally, we outline several challenging issues and possible directions for future research. From this comprehensive literature review, readers can obtain an overview of progress in group activity recognition for future studies.

With the increase in applications of face verification, increasing attention has been paid to their accuracy and security. To ensure both the accuracy and safety of these systems, this paper proposes an encrypted face-verification system. In this paper, face features are extracted using deep neural networks and then encrypted with the Paillier algorithm and saved in a data set. The framework of the whole system involves three parties: the client, data server, and verification server. The data server saves the encrypted user features and user ID, the verification server performs verification, and the client is responsible for collecting a requester's information and sending it to the servers. The information is transmitted among parties as cipher text, which means that no parties know the private keys except for the verification server. The proposed scheme is tested with two deep convolutional neural networks architectures on the labeled faces in the Wild and Faces94 data sets. The extensive experimental results, including results for identification and verification tasks, show that our approach can enhance the security of a recognition system with little decrease in accuracy. Therefore, the proposed system is efficient with respect to both the security and high verification accuracy.