Related papers: TNTC: two-stream network with transformer-based co…
Understanding expressed sentiment and emotions are two crucial factors in human multimodal language. This paper describes a Transformer-based joint-encoding (TBJE) for the task of Emotion Recognition and Sentiment Analysis. In addition to…
We present a module that extends the temporal graph of a graph convolutional network (GCN) for action recognition with a sequence of skeletons. Existing methods attempt to represent a more appropriate spatial graph on an intra-frame, but…
Skeleton-based action recognition has gained significant attention for its ability to efficiently represent spatiotemporal information in a lightweight format. Most existing approaches use graph-based models to process skeleton sequences,…
Many gait recognition methods first partition the human gait into N-parts and then combine them to establish part-based feature representations. Their gait recognition performance is often affected by partitioning strategies, which are…
Skeleton-based Human Activity Recognition has achieved great interest in recent years as skeleton data has demonstrated being robust to illumination changes, body scales, dynamic camera views, and complex background. In particular,…
In this work, we propose a novel Convolutional Neural Network (CNN) architecture for the joint detection and matching of feature points in images acquired by different sensors using a single forward pass. The resulting feature detector is…
People identification in video based on the way they walk (i.e. gait) is a relevant task in computer vision using a non-invasive approach. Standard and current approaches typically derive gait signatures from sequences of binary energy maps…
In terms of human-computer interaction, it is becoming more and more important to correctly understand the user's emotional state in a conversation, so the task of multimodal emotion recognition (MER) started to receive more attention.…
Convolutional Neural Networks (ConvNets) have recently shown promising performance in many computer vision tasks, especially image-based recognition. How to effectively apply ConvNets to sequence-based data is still an open problem. This…
A graph neural network (GNN) for image understanding based on multiple cues is proposed in this paper. Compared to traditional feature and decision fusion approaches that neglect the fact that features can interact and exchange information,…
This paper presents the ARN-LSTM architecture, a novel multi-stream action recognition model designed to address the challenge of simultaneously capturing spatial motion and temporal dynamics in action sequences. Traditional methods often…
Affect (emotion) recognition has gained significant attention from researchers in the past decade. Emotion-aware computer systems and devices have many applications ranging from interactive robots, intelligent online tutor to emotion based…
Nowadays, with the explosive growth of multimodal reviews on social media platforms, multimodal sentiment analysis has recently gained popularity because of its high relevance to these social media posts. Although most previous studies…
Automatic emotion recognition has recently gained significant attention due to the growing popularity of deep learning algorithms. One of the primary challenges in emotion recognition is effectively utilizing the various cues (modalities)…
Skeleton-based gait recognizers excel at modeling spatial configurations but often underuse explicit motion dynamics that are crucial under appearance changes. We introduce a plug-and-play Wavelet Feature Stream that augments any skeleton…
In this work, Transition Probability Matrix (TPM) is proposed as a new method for extracting the features of nodes in the graph. The proposed method uses random walks to capture the connectivity structure of a node's close neighborhood. The…
The fusion technique is the key to the multimodal emotion recognition task. Recently, cross-modal attention-based fusion methods have demonstrated high performance and strong robustness. However, cross-modal attention suffers from redundant…
Affective computing plays a key role in human-computer interactions, entertainment, teaching, safe driving, and multimedia integration. Major breakthroughs have been made recently in the areas of affective computing (i.e., emotion…
As a fundamental aspect of human life, two-person interactions contain meaningful information about people's activities, relationships, and social settings. Human action recognition serves as the foundation for many smart applications, with…
Skeleton-based action recognition methods are limited by the semantic extraction of spatio-temporal skeletal maps. However, current methods have difficulty in effectively combining features from both temporal and spatial graph dimensions…