Search

Hand gesture recognition (HGR) is a crucial area of research that enhances communication by overcoming language barriers and facilitating human-computer interaction. Although previous works in HGR have employed deep neural networks, they fail to encode the orientation and position of the hand in the image. To address this issue, this paper proposes HGR-ViT, a Vision Transformer (ViT) model with an attention mechanism for hand gesture recognition. Given a hand gesture image, it is first split into fixed size patches. Positional embedding is added to these embeddings to form learnable vectors that capture the positional information of the hand patches. The resulting sequence of vectors are then served as the input to a standard Transformer encoder to obtain the hand gesture representation. A multilayer perceptron head is added to the output of the encoder to classify the hand gesture to the correct class. The proposed HGR-ViT obtains an accuracy of 99.98%, 99.36% and 99.85% for the American Sign Language (ASL) dataset, ASL with Digits dataset, and National University of Singapore (NUS) hand gesture dataset, respectively.

Human action recognition is a constantly evolving field that is driven by numerous applications. In recent years, significant progress has been made in this area due to the development of advanced representation learning techniques. Despite this progress, human action recognition still poses significant challenges, particularly due to the unpredictable variations in the visual appearance of an image sequence. To address these challenges, we propose the fine-tuned temporal dense sampling with 1D convolutional neural network (FTDS-1DConvNet). Our method involves the use of temporal segmentation and temporal dense sampling, which help to capture the most important features of a human action video. First, the human action video is partitioned into segments through temporal segmentation. Each segment is then processed through a fine-tuned Inception-ResNet-V2 model, where max pooling is performed along the temporal axis to encode the most significant features as a fixed-length representation. This representation is then fed into a 1DConvNet for further representation learning and classification. The experiments on UCF101 and HMDB51 demonstrate that the proposed FTDS-1DConvNet outperforms the state-of-the-art methods, with a classification accuracy of 88.43% on the UCF101 dataset and 56.23% on the HMDB51 dataset.

Mesh-based 3-dimensional (3D) shape generation from a 2-dimensional (2D) image using a convolution neural network (CNN) framework is an open problem in the computer graphics and vision domains. Most existing CNN-based frameworks lack robust algorithms that can scale well without combining different shape parts. Also, most CNN-based algorithms lack suitable 3D data representations that can fit into CNN without modification(s) to produce high-quality 3D shapes. This paper presents an approach that integrates a variational autoencoder (VAE) and a generative adversarial network (GAN) called 3 dimensional variational autoencoder signed distance function generative adversarial network (3D-VAE-SDFGAN) to create a 3D shape from a 2D image that considerably improves scalability and visual quality. The proposed method only feeds a single 2D image into the network to produce a mesh-based 3D shape. The network encodes a 2D image of the 3D object into the latent representations, and implicit surface representations of 3D objects corresponding to those 2D images are subsequently generated. Hence, a signed distance function (SDF) is proposed to maintain object inside-outside information in the implicit surface representation. Polygon mesh surfaces are then produced using the marching cubes algorithm. The ShapeNet dataset was used in the experiments to evaluate the proposed 3D-VAE-SDFGAN. The experimental results show that 3D-VAE-SDFGAN outperforms other state-of-the-art models.

The spectacular growth of wearable sensors has provided a key contribution to the field of human activity recognition. Due to its effective and versatile usage and application in various fields such as smart homes and medical areas, human activity recognition has always been an appealing research topic in artificial intelligence. From this perspective, there are a lot of existing works that make use of accelerometer and gyroscope sensor data for recognizing human activities. This paper presents a comparative study of ensemble learning methods for human activity recognition. The methods include random forest, adaptive boosting, gradient boosting, extreme gradient boosting, and light gradient boosting machine (LightGBM). Among the ensemble learning methods in comparison, light gradient boosting machine and random forest demonstrate the best performance. The experimental results revealed that light gradient boosting machine yields the highest accuracy of 94.50% on UCI-HAR dataset and 100% on single accelerometer dataset while random forest records the highest accuracy of 93.41% on motion sense dataset.

Speech emotion recognition aims to identify the emotion expressed in the speech by analyzing the audio signals. In this work, data augmentation is first performed on the audio samples to increase the number of samples for better model learning. The audio samples are comprehensively encoded as the frequency and temporal domain features. In the classification, a light gradient boosting machine is leveraged. The hyperparameter tuning of the light gradient boosting machine is performed to determine the optimal hyperparameter settings. As the speech emotion recognition datasets are imbalanced, the class weights are regulated to be inversely proportional to the sample distribution where minority classes are assigned higher class weights. The experimental results demonstrate that the proposed method outshines the state-of-the-art methods with 84.91% accuracy on the emo-DB dataset, 67.72% on the Ryerson audio-visual database of emotional speech and song (RAVDESS) dataset, and 62.94% on the interactive emotional dyadic motion capture (IEMOCAP) dataset.