Related papers: STAR-GNN: Spatial-Temporal Video Representation fo…
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…
Accurate video understanding involves reasoning about the relationships between actors, objects and their environment, often over long temporal intervals. In this paper, we propose a message passing graph neural network that explicitly…
A central question in neuroscience is how self-organizing dynamic interactions in the brain emerge on their relatively static structural backbone. Due to the complexity of spatial and temporal dependencies between different brain areas,…
It is difficult for people to interpret the decision-making in the inference process of deep neural networks. Visual explanation is one method for interpreting the decision-making of deep learning. It analyzes the decision-making of 2D CNNs…
Video-based visible-infrared person re-identification (VVI-ReID) is challenging due to significant modality feature discrepancies. Spatial-temporal information in videos is crucial, but the accuracy of spatial-temporal information is often…
The current paper proposes a novel neural network model for recognizing visually perceived human actions. The proposed multiple spatio-temporal scales recurrent neural network (MSTRNN) model is derived by introducing multiple timescale…
With recent advances in sensing technologies, a myriad of spatio-temporal data has been generated and recorded in smart cities. Forecasting the evolution patterns of spatio-temporal data is an important yet demanding aspect of urban…
Biological spiking neurons with intrinsic dynamics underlie the powerful representation and learning capabilities of the brain for processing multimodal information in complex environments. Despite recent tremendous progress in spiking…
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 address the challenging task of cross-modal moment retrieval, which aims to localize a temporal segment from an untrimmed video described by a natural language query. It poses great challenges over the proper semantic alignment between…
In the field of action recognition, video clips are always treated as ordered frames for subsequent processing. To achieve spatio-temporal perception, existing approaches propose to embed adjacent temporal interaction in the convolutional…
GNNs have been proven to perform highly effective in various node-level, edge-level, and graph-level prediction tasks in several domains. Existing approaches mainly focus on static graphs. However, many graphs change over time with their…
Spatiotemporal data can be represented as a process over a graph, which captures their spatial relationships either explicitly or implicitly. How to leverage such a structure for learning representations is one of the key challenges when…
Video-based person re-identification (Re-ID) aims at matching video sequences of pedestrians across non-overlapping cameras. It is a practical yet challenging task of how to embed spatial and temporal information of a video into its feature…
Capturing long-range dependencies in feature representations is crucial for many visual recognition tasks. Despite recent successes of deep convolutional networks, it remains challenging to model non-local context relations between visual…
Temporal reasoning is an important aspect of video analysis. 3D CNN shows good performance by exploring spatial-temporal features jointly in an unconstrained way, but it also increases the computational cost a lot. Previous works try to…
In the realm of applications where data dynamically evolves across spatial and temporal dimensions, Graph Neural Networks (GNNs) are often complemented by sequence modeling architectures, such as RNNs and transformers, to effectively model…
Previous works for LiDAR-based 3D object detection mainly focus on the single-frame paradigm. In this paper, we propose to detect 3D objects by exploiting temporal information in multiple frames, i.e., the point cloud videos. We empirically…
We present a generic framework for spatio-temporal (ST) data modeling, analysis, and forecasting, with a special focus on data that is sparse in both space and time. Our multi-scaled framework is a seamless coupling of two major components:…
We present a new method for finding video CNN architectures that capture rich spatio-temporal information in videos. Previous work, taking advantage of 3D convolutions, obtained promising results by manually designing video CNN…