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.

Due to the complementary properties of different types of sensors, change detection between heterogeneous images receives increasing attention from researchers. However, change detection cannot be handled by directly comparing two heterogeneous images since they demonstrate different image appearances and statistics. In this article, we propose a deep pyramid feature learning network (DPFL-Net) for change detection, especially between heterogeneous images. DPFL-Net can learn a series of hierarchical features in an unsupervised fashion, containing both spatial details and multiscale contextual information. The learned pyramid features from two input images make unchanged pixels matched exactly and changed ones dissimilar and after transformed into the same space for each scale successively. We further propose fusion blocks to aggregate multiscale difference images (DIs), generating an enhanced DI with strong separability. Based on the enhanced DI, unchanged areas are predicted and used to train DPFL-Net in the next iteration. In this article, pyramid features and unchanged areas are updated alternately, leading to an unsupervised change detection method. In the feature transformation process, local consistency is introduced to constrain the learned pyramid features, modeling the correlations between the neighboring pixels and reducing the false alarms. Experimental results demonstrate that the proposed approach achieves superior or at least comparable results to the existing state-of-the-art change detection methods in both homogeneous and heterogeneous cases.

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.

Shot boundary detection is essentially to detect the position of frames where the shot changes. It has been actively studied in video analysis and management for convenience, which becomes a key technique with the rapid proliferation of rich and diverse videos. With respect to the complex characteristics of different shots in varying length and content variation property, in this paper we present a two stage method for shot boundary detection (TSSBD) which distinguishes abrupt shot by fusing color histogram and deep features and locate gradual shot changes with C3D based deep analysis. Abrupt shot changes are detected firstly as it occurs between two frames, which divides the complete video into segments containing gradual transitions; Over these video segments, gradual shot change detection is implemented using 3D-convolutional neural network, which classifies clips into specific gradual shot change types; Finally, an effective merging strategy is proposed to locate positions of gradual shot transitions. The experimental analysis illustrates that the proposed progressive method is capable of detecting both abrupt shot transitions and gradual shot transitions accurately.