Related papers: Spatio-Temporal Interaction Graph Parsing Networks…
We propose novel Stacked Spatio-Temporal Graph Convolutional Networks (Stacked-STGCN) for action segmentation, i.e., predicting and localizing a sequence of actions over long videos. We extend the Spatio-Temporal Graph Convolutional Network…
Temporal Video Grounding (TVG) aims to localize temporal moments in an untrimmed video that semantically correspond to given natural language queries. Recently, Graph Convolutional Networks (GCN) have been widely adopted in TVG to model…
With advances in data-driven machine learning research, a wide variety of prediction models have been proposed to capture spatio-temporal features for the analysis of video streams. Recognising actions and detecting action transitions…
Spatio-temporal scene graphs provide a principled representation for modeling evolving object interactions, yet existing methods remain fundamentally frame-centric: they reason only about currently visible objects, discard entities upon…
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…
Graph Neural Networks are perfectly suited to capture latent interactions between various entities in the spatio-temporal domain (e.g. videos). However, when an explicit structure is not available, it is not obvious what atomic elements…
Identifying objects in an image and their mutual relationships as a scene graph leads to a deep understanding of image content. Despite the recent advancement in deep learning, the detection and labeling of visual object relationships…
Deep Recurrent Neural Network architectures, though remarkably capable at modeling sequences, lack an intuitive high-level spatio-temporal structure. That is while many problems in computer vision inherently have an underlying high-level…
Learning in the space-time domain remains a very challenging problem in machine learning and computer vision. Current computational models for understanding spatio-temporal visual data are heavily rooted in the classical single-image based…
Current state-of-the-art approaches for spatio-temporal action localization rely on detections at the frame level and model temporal context with 3D ConvNets. Here, we go one step further and model spatio-temporal relations to capture the…
Learning structured task representations from human demonstrations is essential for understanding long-horizon manipulation behaviors, particularly in bimanual settings where action ordering, object involvement, and interaction geometry can…
Human skeleton information is important in skeleton-based action recognition, which provides a simple and efficient way to describe human pose. However, existing skeleton-based methods focus more on the skeleton, ignoring the objects…
Video-based person re-identification aims to match pedestrians from video sequences across non-overlapping camera views. The key factor for video person re-identification is to effectively exploit both spatial and temporal clues from video…
Person Re-Identification (person re-id) is a crucial task as its applications in visual surveillance and human-computer interaction. In this work, we present a novel joint Spatial and Temporal Attention Pooling Network (ASTPN) for…
Graph convolutional networks (GCNs) can effectively capture the features of related nodes and improve the performance of the model. More attention is paid to employing GCN in Skeleton-Based action recognition. But existing methods based on…
Accurate and timely traffic flow forecasting is crucial for intelligent transportation systems. This paper presents a novel deep learning model, the Spatial-Temporal Unified Graph Attention Network (STGAtt). By leveraging a unified graph…
Anomaly identification is highly dependent on the relationship between the object and the scene, as different/same object actions in same/different scenes may lead to various degrees of normality and anomaly. Therefore, object-scene…
Accurate forecasting of citywide traffic flow has been playing critical role in a variety of spatial-temporal mining applications, such as intelligent traffic control and public risk assessment. While previous work has made significant…
Text-based visual question answering (TextVQA) faces the significant challenge of avoiding redundant relational inference. To be specific, a large number of detected objects and optical character recognition (OCR) tokens result in rich…
Traffic forecasting has emerged as a core component of intelligent transportation systems. However, timely accurate traffic forecasting, especially long-term forecasting, still remains an open challenge due to the highly nonlinear and…