Related papers: Temporal Relational Modeling with Self-Supervision…
Well-designed open-source software drives progress in Machine Learning (ML) research. While static graph ML enjoys mature frameworks like PyTorch Geometric and DGL, ML for temporal graphs (TG), networks that evolve over time, lacks…
Dynamic community detection has been prospered as a powerful tool for quantifying changes in dynamic brain network connectivity patterns by identifying strongly connected sets of nodes. However, as the network science problems and network…
Large language models (LLMs) have demonstrated strong performance in natural language generation but remain limited in knowle- dge-intensive tasks due to outdated or incomplete internal knowledge. Retrieval-Augmented Generation (RAG)…
Human actions captured in video sequences contain two crucial factors for action recognition, i.e., visual appearance and motion dynamics. To model these two aspects, Convolutional and Recurrent Neural Networks (CNNs and RNNs) are adopted…
While state-of-the-art 3D Convolutional Neural Networks (CNN) achieve very good results on action recognition datasets, they are computationally very expensive and require many GFLOPs. While the GFLOPs of a 3D CNN can be decreased by…
This paper describes a temporal-spatial model for video processing with special applications to processing event camera videos. We propose to study a conjecture motivated by our previous study of video processing with delay loop reservoir…
The work in this paper is driven by the question how to exploit the temporal cues available in videos for their accurate classification, and for human action recognition in particular? Thus far, the vision community has focused on…
Video action segmentation have been widely applied in many fields. Most previous studies employed video-based vision models for this purpose. However, they often rely on a large receptive field, LSTM or Transformer methods to capture…
Extracting temporal and representation features efficiently plays a pivotal role in understanding visual sequence information. To deal with this, we propose a new recurrent neural framework that can be stacked deep effectively. There are…
Dynamic graphs are common in real-world systems such as social media, recommender systems, and traffic networks. Existing dynamic graph models for link prediction often fall short in capturing the complexity of temporal evolution. They tend…
Many real-world systems can be expressed in temporal networks with nodes playing far different roles in structure and function and edges representing the relationships between nodes. Identifying critical nodes can help us control the spread…
Dynamic Text-Attribute Graphs (DyTAGs), characterized by time-evolving graph interactions and associated text attributes, are prevalent in real-world applications. Existing methods, such as Graph Neural Networks (GNNs) and Large Language…
Temporal Grounding is to identify specific moments or highlights from a video corresponding to textual descriptions. Typical approaches in temporal grounding treat all video clips equally during the encoding process regardless of their…
Action visual tempo characterizes the dynamics and the temporal scale of an action, which is helpful to distinguish human actions that share high similarities in visual dynamics and appearance. Previous methods capture the visual tempo…
Many methods for learning from video sequences involve temporally processing 2D CNN features from the individual frames or directly utilizing 3D convolutions within high-performing 2D CNN architectures. The focus typically remains on how to…
Semi-supervised video action recognition tends to enable deep neural networks to achieve remarkable performance even with very limited labeled data. However, existing methods are mainly transferred from current image-based methods (e.g.,…
Skeleton-based human action recognition has attracted much attention with the prevalence of accessible depth sensors. Recently, graph convolutional networks (GCNs) have been widely used for this task due to their powerful capability to…
Temporal link prediction in dynamic graphs is a fundamental problem in many real-world systems. Existing temporal graph neural networks mainly focus on learning representations of historical interactions. Despite their strong performance,…
Traffic flow forecasting is of great significance for improving the efficiency of transportation systems and preventing emergencies. Due to the highly non-linearity and intricate evolutionary patterns of short-term and long-term traffic…
Spatiotemporal graph convolutional networks (STGCNs) have emerged as a desirable model for skeleton-based human action recognition. Despite achieving state-of-the-art performance, there is a limited understanding of the representations…