Related papers: STMT: A Spatial-Temporal Mesh Transformer for MoCa…
Skeleton-based human action recognition has achieved a great interest in recent years, as skeleton data has been demonstrated to be robust to illumination changes, body scales, dynamic camera views, and complex background. Nevertheless, an…
The task of action detection aims at deducing both the action category and localization of the start and end moment for each action instance in a long, untrimmed video. While vision Transformers have driven the recent advances in video…
Capturing the dependencies between joints is critical in skeleton-based action recognition task. Transformer shows great potential to model the correlation of important joints. However, the existing Transformer-based methods cannot capture…
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,…
We propose ST-DETR, a Spatio-Temporal Transformer-based architecture for object detection from a sequence of temporal frames. We treat the temporal frames as sequences in both space and time and employ the full attention mechanisms to take…
Multi-object tracking (MOT) has profound applications in a variety of fields, including surveillance, sports analytics, self-driving, and cooperative robotics. Despite considerable advancements, existing MOT methodologies tend to falter…
Recent technological advancements have significantly expanded the potential of human action recognition through harnessing the power of 3D data. This data provides a richer understanding of actions, including depth information that enables…
It's common for current methods in skeleton-based action recognition to mainly consider capturing long-term temporal dependencies as skeleton sequences are typically long (>128 frames), which forms a challenging problem for previous…
Previous methods for dynamic facial expression in the wild are mainly based on Convolutional Neural Networks (CNNs), whose local operations ignore the long-range dependencies in videos. To solve this problem, we propose the spatio-temporal…
Skeleton-based gesture recognition methods have achieved high success using Graph Convolutional Network (GCN). In addition, context-dependent adaptive topology as a neighborhood vertex information and attention mechanism leverages a model…
We introduce Spatial-Temporal Memory Networks for video object detection. At its core, a novel Spatial-Temporal Memory module (STMM) serves as the recurrent computation unit to model long-term temporal appearance and motion dynamics. The…
Temporal human action detection aims to identify and localize action segments within untrimmed videos, serving as a pivotal task in video understanding. Despite the progress achieved by prior architectures like CNN and Transformer models,…
Effective learning of spatial-temporal information within a point cloud sequence is highly important for many down-stream tasks such as 4D semantic segmentation and 3D action recognition. In this paper, we propose a novel framework named…
Human Action Recognition (HAR) is an interesting research area in human-computer interaction used to monitor the activities of elderly and disabled individuals affected by physical and mental health. In the recent era, skeleton-based HAR…
Skeleton-based action recognition, which classifies human actions based on the coordinates of joints and their connectivity within skeleton data, is widely utilized in various scenarios. While Graph Convolutional Networks (GCNs) have been…
Skeleton-based human action recognition has attracted a lot of research attention during the past few years. Recent works attempted to utilize recurrent neural networks to model the temporal dependencies between the 3D positional…
Modeling neural population dynamics underlying noisy single-trial spiking activities is essential for relating neural observation and behavior. A recent non-recurrent method - Neural Data Transformers (NDT) - has shown great success in…
This paper presents a novel spatiotemporal transformer network that introduces several original components to detect actions in untrimmed videos. First, the multi-feature selective semantic attention model calculates the correlations…
The modeling, computational cost, and accuracy of traditional Spatio-temporal networks are the three most concentrated research topics in video action recognition. The traditional 2D convolution has a low computational cost, but it cannot…
Video scene graph generation (VidSGG) aims to identify objects in visual scenes and infer their relationships for a given video. It requires not only a comprehensive understanding of each object scattered on the whole scene but also a deep…