The technology used in smart homes have improved to learn the user preferences from feedbacks in order to provide convenience to the user in the home environment. Most smart homes learn a uniform model to represent the thermal preference of user which generally fails when the pool of occupants includes people having different age, gender, and location. Having different thermal sensation for each user poses a challenge for the smart homes to learn a personalized preference for each occupant without forgetting the policy of others. A smart home with single optimal policy may fail to provide comfort when a new user with different preference is integrated in the home. In this paper, we propose POSHS, a Bayesian Reinforcement learning algorithm that can approximate the current occupant state in a partial observable environment using its thermal preference and then decide if its a new occupant or belongs to the pool of previously observed users. We then compare POSHS algorithm with an LSTM based algorithm to learn and estimate the current state of the occupant while also taking optimal actions to reduce the timesteps required to set the preferences. We perform these experiments with upto 5 simulated human models each based on hierarchical reinforcement learning. The results show that POSHS can approximate the current user state just from its temperature and humidity preference and also reduce the number of time-steps required to set optimal temperature and humidity by the human model in the presence of the smart home.
We present CrissCross, a self-supervised framework for learning audio-visual representations. A novel notion is introduced in our framework whereby in addition to learning the intra-modal and standard 'synchronous' cross-modal relations, CrissCross also learns 'asynchronous' cross-modal relationships. We show that by relaxing the temporal synchronicity between the audio and visual modalities, the network learns strong time-invariant representations. Our experiments show that strong augmentations for both audio and visual modalities with relaxation of cross-modal temporal synchronicity optimize performance. To pretrain our proposed framework, we use 3 different datasets with varying sizes, Kinetics-Sound, Kinetics-400, and AudioSet. The learned representations are evaluated on a number of downstream tasks namely action recognition, sound classification, and retrieval. CrissCross shows state-of-the-art performances on action recognition (UCF101 and HMDB51) and sound classification (ESC50). The codes and pretrained models will be made publicly available.
Hand pose estimation (HPE) can be used for a variety of human-computer interaction applications such as gesture-based control for physical or virtual/augmented reality devices. Recent works have shown that videos or multi-view images carry rich information regarding the hand, allowing for the development of more robust HPE systems. In this paper, we present the Multi-View Video-Based 3D Hand (MuViHand) dataset, consisting of multi-view videos of the hand along with ground-truth 3D pose labels. Our dataset includes more than 402,000 synthetic hand images available in 4,560 videos. The videos have been simultaneously captured from six different angles with complex backgrounds and random levels of dynamic lighting. The data has been captured from 10 distinct animated subjects using 12 cameras in a semi-circle topology where six tracking cameras only focus on the hand and the other six fixed cameras capture the entire body. Next, we implement MuViHandNet, a neural pipeline consisting of image encoders for obtaining visual embeddings of the hand, recurrent learners to learn both temporal and angular sequential information, and graph networks with U-Net architectures to estimate the final 3D pose information. We perform extensive experiments and show the challenging nature of this new dataset as well as the effectiveness of our proposed method. Ablation studies show the added value of each component in MuViHandNet, as well as the benefit of having temporal and sequential information in the dataset.
Recently, supervised methods, which often require substantial amounts of class labels, have achieved promising results for EEG representation learning. However, labeling EEG data is a challenging task. More recently, holistic semi-supervised learning approaches, which only require few output labels, have shown promising results in the field of computer vision. These methods, however, have not yet been adapted for EEG learning. In this paper, we adapt three state-of-the-art holistic semi-supervised approaches, namely MixMatch, FixMatch, and AdaMatch, as well as five classical semi-supervised methods for EEG learning. We perform rigorous experiments with all 8 methods on two public EEG-based emotion recognition datasets, namely SEED and SEED-IV. The experiments with different amounts of limited labeled samples show that the holistic approaches achieve strong results even when only 1 labeled sample is used per class. Further experiments show that in most cases, AdaMatch is the most effective method, followed by MixMatch and FixMatch.
Automatic classification of running styles can enable runners to obtain feedback with the aim of optimizing performance in terms of minimizing energy expenditure, fatigue, and risk of injury. To develop a system capable of classifying running styles using wearables, we collect a dataset from 10 healthy runners performing 8 different pre-defined running styles. Five wearable devices are used to record accelerometer data from different parts of the lower body, namely left and right foot, left and right medial tibia, and lower back. Using the collected dataset, we develop a deep learning solution which consists of a Convolutional Neural Network and Long Short-Term Memory network to first automatically extract effective features, followed by learning temporal relationships. Score-level fusion is used to aggregate the classification results from the different sensors. Experiments show that the proposed model is capable of automatically classifying different running styles in a subject-dependant manner, outperforming several classical machine learning methods (following manual feature extraction) and a convolutional neural network baseline. Moreover, our study finds that subject-independent classification of running styles is considerably more challenging than a subject-dependant scheme, indicating a high level of personalization in such running styles. Finally, we demonstrate that by fine-tuning the model with as few as 5% subject-specific samples, considerable performance boost is obtained.
Electrocardiogram (ECG) has been widely used for emotion recognition. This paper presents a deep neural network based on convolutional layers and a transformer mechanism to detect stress using ECG signals. We perform leave-one-subject-out experiments on two publicly available datasets, WESAD and SWELL-KW, to evaluate our method. Our experiments show that the proposed model achieves strong results, comparable or better than the state-of-the-art models for ECG-based stress detection on these two datasets. Moreover, our method is end-to-end, does not require handcrafted features, and can learn robust representations with only a few convolutional blocks and the transformer component.
Facial expression recognition (FER) has emerged as an important component of human-computer interaction systems. Despite recent advancements in FER, performance often drops significantly for non-frontal facial images. We propose Contrastive Learning of Multi-view facial Expressions (CL-MEx) to exploit facial images captured simultaneously from different angles towards FER. CL-MEx is a two-step training framework. In the first step, an encoder network is pre-trained with the proposed self-supervised contrastive loss, where it learns to generate view-invariant embeddings for different views of a subject. The model is then fine-tuned with labeled data in a supervised setting. We demonstrate the performance of the proposed method on two multi-view FER datasets, KDEF and DDCF, where state-of-the-art performances are achieved. Further experiments show the robustness of our method in dealing with challenging angles and reduced amounts of labeled data.
We propose a self-supervised contrastive learning approach for facial expression recognition (FER) in videos. We propose a novel temporal sampling-based augmentation scheme to be utilized in addition to standard spatial augmentations used for contrastive learning. Our proposed temporal augmentation scheme randomly picks from one of three temporal sampling techniques: (1) pure random sampling, (2) uniform sampling, and (3) sequential sampling. This is followed by a combination of up to three standard spatial augmentations. We then use a deep R(2+1)D network for FER, which we train in a self-supervised fashion based on the augmentations and subsequently fine-tune. Experiments are performed on the Oulu-CASIA dataset and the performance is compared to other works in FER. The results indicate that our method achieves an accuracy of 89.4%, setting a new state-of-the-art by outperforming other works. Additional experiments and analysis confirm the considerable contribution of the proposed temporal augmentation versus the existing spatial ones.