In recent times, as interest in stress control has increased, many studies on stress recognition have been conducted. Several studies have been based on physiological signals, but the disadvantage of this strategy is that it requires physiological-signal-acquisition devices. Another strategy employs facial-image-based stress-recognition methods, which do not require devices, but predominantly use handcrafted features. However, such features have low discriminating power. We propose a deep-learning-based stress-recognition method using facial images to address these challenges. Given that deep-learning methods require extensive data, we constructed a large-capacity image database for stress recognition. Furthermore, we used temporal attention, which assigns a high weight to frames that are highly related to stress, as well as spatial attention, which assigns a high weight to regions that are highly related to stress. By adding a network that inputs the facial landmark information closely related to stress, we supplemented the network that receives only facial images as the input. Experimental results on our newly constructed database indicated that the proposed method outperforms contemporary deep-learning-based recognition methods.

In recent days, unmanned aerial vehicles (UAVs) becomes more familiar because of its versatility, automation abilities, and low cost. Dynamic scene classification gained significant interest among the UAV-based surveillance systems, e.g., high-voltage power line and forest fire monitoring, which facilitate the object detection, tracking process and drastically enhances the outcome of visual surveillance. This paper proposes a new optimal deep learning-based scene classification model captured by UAVs. The proposed model involves a residual network-based features extraction (RNBFE) which extracts features from the diverse convolution layers of a deep residual network. In addition, the several parameters in RNBFE lead to many configuration errors due to manual parameter tuning. So, self-adaptive global best harmony search (SGHS) algorithm is employed for tuning the parameters of the RNBFE. The resultant feature vectors undergo classification by the use of latent variable support vector machine (LVSVM) model. The presented optimal RNBFE (ORNBFE) model has been tested using two open access datasets namely UC Merced (UCM) Land Use Dataset and WHU-RS Dataset. The presented technique attains maximum scene classification accuracy over the other recently proposed methods.

Reducing the cross-modality gap between two different domains is a challenging problem for heterogeneous face recognition (HFR). The current visual domain face recognition system is not easy to solve the discrepancy of cross-modality when two comparing domains are heterogeneous. Moreover, the amount of HFR dataset is significantly insufficient, making it considerable difficulty in training. This paper proposes a novel two-step framework that consists of the image translation module and the feature learning module to obtain an enhanced cross-modality matching system for heterogeneous datasets. First, the image translation module consists of a Preprocessing Chain (PC) method, CycleGAN, and the Siamese network. It enables to meet the conditions for preserving contents along with changing the styles from the source domain to the target domain. Second, in the feature learning module, the training dataset and its translated images are used together for fine-tuning the pre-trained backbone model in the visual domain. This allows for discriminative and robust feature matching of the probe and gallery test datasets in the visual domain. The experimental results are evaluated with two scenarios, using the CUHK Face Sketch FERET (CUFSF) dataset and the CASIA NIR-VIS 2.0 dataset. The proposed method achieves a better recognition performance in comparison to the state-of-the-art methods.

Most facial analysis methods perform well in standardized testing but not in real-world testing. The main reason is that training models cannot easily learn various human features and background noise, especially for facial landmark detection and head pose estimation tasks with limited and noisy training datasets. To alleviate the gap between standardized and real-world testing, we propose a pseudo-labeling technique using a face recognition dataset consisting of various people and background noise. The use of our pseudo-labeled training dataset can help to overcome the lack of diversity among the people in the dataset. Our integrated framework is constructed using complementary multitask learning methods to extract robust features for each task. Furthermore, introducing pseudo-labeling and multitask learning improves the face recognition performance by enabling the learning of pose-invariant features. Our method achieves state-of-the-art (SOTA) or near-SOTA performance on the AFLW2000-3D and BIWI datasets for facial landmark detection and head pose estimation, with competitive face verification performance on the IJB-C test dataset for face recognition. We demonstrate this through a novel testing methodology that categorizes cases as soft, medium, and hard based on the pose values of IJB-C. The proposed method achieves stable performance even when the dataset lacks diverse face identifications.

Speech-driven 3D facial animation models are piv otal components in a variety of human interaction systems. However, speech-driven methods are strongly dependent on the quality of input speech, and there are no ways of flexibly changing the content of the speech without re-recording, which can be costly and time-consuming. Using text-to-speech (TTS) as an intermediate step offers an avenue to generate 3D avatars for any content, but involves an inefficient pipeline: converting text to speech and subsequently generating a 3D avatar from the synthesized speech. In order to overcome this constraint, we propose a novel approach for 3D facial animation that effectively merges these two domains. Our model takes advantage of intermediate features derived from the alignment of text and speech, which are then utilized as input for an avatar decoder to transform them into the vertices of a 3D facial animation. By jointly modeling lip movements, text, and speech characteristics, we are able to achieve exceptional performance while substantially reducing the number of model parameters and computational complexity. We demonstrate the efficacy of our model by assessing it in terms of the mean square error of 3D mesh vertices and through a user study that includes ABX test comparisons.