The proposed method has 30 streams, i.e., 15 spatial streams and 15 temporal streams. Each spatial stream corresponds to each temporal stream. Therefore, this work correlates with the symmetry concept. It is a difficult task to classify video-based facial expression owing to the gap between the visual descriptors and the emotions. In order to bridge the gap, a new video descriptor for facial expression recognition is presented to aggregate spatial and temporal convolutional features across the entire extent of a video. The designed framework integrates a state-of-the-art 30 stream and has a trainable spatial–temporal feature aggregation layer. This framework is end-to-end trainable for video-based facial expression recognition. Thus, this framework can effectively avoid overfitting to the limited emotional video datasets, and the trainable strategy can learn to better represent an entire video. The different schemas for pooling spatial–temporal features are investigated, and the spatial and temporal streams are best aggregated by utilizing the proposed method. The extensive experiments on two public databases, BAUM-1s and eNTERFACE05, show that this framework has promising performance and outperforms the state-of-the-art strategies.

Microscopic 3D shape reconstruction using depth from focus (DFF) is crucial in precision manufacturing for 3D modeling and quality control. However, the absence of high-precision microscopic DFF datasets and the significant differences between existing DFF datasets and microscopic DFF data in optical design, imaging principles and scene characteristics hinder the performance of current DFF models in microscopic tasks. To address this, we introduce M3D, a novel microscopic DFF dataset, constructed using a self-developed microscopic device. It includes multi-focus image sequences of 1,952 scenes across five categories, with depth labels obtained through the 3D TFT algorithm applied to dense image sequences for initial depth estimation and calibration. All labels are then compared and analyzed against the design values, and those with large errors are eliminated. We also propose M3DNet, a frequency-aware end-to-end network, to tackle challenges like shallow depth-of-field (DoF) and weak textures. Results show that M3D compensates for the limitations of macroscopic DFF datasets and extends DFF applications to microscopic scenarios. M3DNet effectively captures rapid focus decay and improves performance on public DFF datasets by leveraging superior global feature extraction. Additionally, it exhibits strong robustness even in extreme conditions. Dataset and code are available at https://github.com/jiangfeng-Z/M3D.

Aiming at the problem that the accuracy of small target segmentation is not high in complex scenes, this paper proposes a target segmentation method based on attention mechanism. The convolutional neural network extract the feature maps based on VGG16, and extract multi directional feature as the horizontal and vertical feature maps in low layer networks, which can effectively fuse and enrich the context information. Moreover, combined with the attention mechanism, the relationship between the channels of feature maps is learned adaptively. The useful information is emphasized, and the redundant information is suppressed. The discrimination ability of feature maps is improved. The enhanced feature maps are then used for segmentation. The experimental results show that, compared with similar algorithms, the proposed algorithm has better segmentation effect for most small targets and significantly improves the segmentation accuracy.