Related papers: Spatio-Temporal Tuples Transformer for Skeleton-Ba…
Graph Convolutional Networks (GCNs) have been widely used to model the high-order dynamic dependencies for skeleton-based action recognition. Most existing approaches do not explicitly embed the high-order spatio-temporal importance to…
Recently, Transformer-based networks have shown great promise on skeleton-based action recognition tasks. The ability to capture global and local dependencies is the key to success while it also brings quadratic computation and memory cost.…
In skeleton-based human action recognition, temporal pooling is a critical step for capturing spatiotemporal relationship of joint dynamics. Conventional pooling methods overlook the preservation of motion information and treat each frame…
Effectively modeling discriminative spatio-temporal information is essential for segmenting activities in long action sequences. However, we observe that existing methods are limited in weak spatio-temporal modeling capability due to two…
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…
Video snapshot compressive imaging (SCI) captures multiple sequential video frames by a single measurement using the idea of computational imaging. The underlying principle is to modulate high-speed frames through different masks and these…
The dynamics of human skeletons have significant information for the task of action recognition. The similarity between trajectories of corresponding joints is an indicating feature of the same action, while this similarity may subject to…
Action recognition from multi-modal and multi-view observations holds significant potential for applications in surveillance, robotics, and smart environments. However, existing methods often fall short of addressing real-world challenges…
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…
Movement synchrony reflects the coordination of body movements between interacting dyads. The estimation of movement synchrony has been automated by powerful deep learning models such as transformer networks. However, instead of designing a…
The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. In this paper, we propose a novel solution named TransSTAM, which leverages Transformer to effectively model…
In this paper, we propose a coupled spatial-temporal attention (CSTA) model for skeleton-based action recognition, which aims to figure out the most discriminative joints and frames in spatial and temporal domains simultaneously.…
Graph convolutional networks (GCNs) are widely adopted in skeleton-based action recognition due to their powerful ability to model data topology. We argue that the performance of recent proposed skeleton-based action recognition methods is…
Transformer-based approaches have been successfully proposed for 3D human pose estimation (HPE) from 2D pose sequence and achieved state-of-the-art (SOTA) performance. However, current SOTAs have difficulties in modeling spatial-temporal…
Consecutive frames in a video contain redundancy, but they may also contain relevant complementary information for the detection task. The objective of our work is to leverage this complementary information to improve detection. Therefore,…
We propose a novel Transformer-based architecture for the task of generative modelling of 3D human motion. Previous work commonly relies on RNN-based models considering shorter forecast horizons reaching a stationary and often implausible…
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,…
This paper presents a new method for 3D action recognition with skeleton sequences (i.e., 3D trajectories of human skeleton joints). The proposed method first transforms each skeleton sequence into three clips each consisting of several…
Tracking multiple objects in videos relies on modeling the spatial-temporal interactions of the objects. In this paper, we propose a solution named TransMOT, which leverages powerful graph transformers to efficiently model the spatial and…
Group activity recognition is a crucial yet challenging problem, whose core lies in fully exploring spatial-temporal interactions among individuals and generating reasonable group representations. However, previous methods either model…