Related papers: Spatio-Temporal Proximity-Aware Dual-Path Model fo…

Network modeling characterizes the underlying principles of structural properties and is of vital significance for simulating dynamical processes in real world. However, bridging structure and dynamics is always challenging due to the…

Multi-modality is an important feature of sensor based activity recognition. In this work, we consider two inherent characteristics of human activities, the spatially-temporally varying salience of features and the relations between…

The problem of active mapping aims to plan an informative sequence of sensing views given a limited budget such as distance traveled. This paper consider active occupancy grid mapping using a range sensor, such as LiDAR or depth camera.…

Human Activity Recognition~(HAR) is the classification of human movement, captured using one or more sensors either as wearables or embedded in the environment~(e.g. depth cameras, pressure mats). State-of-the-art methods of HAR rely on…

Forecasting 3D human motion is an important embodiment of fine-grained understanding and cognition of human behavior by artificial agents. Current approaches excessively rely on implicit network modeling of spatiotemporal relationships and…

Group Activity Recognition aims to understand collective activities from videos. Existing solutions primarily rely on the RGB modality, which encounters challenges such as background variations, occlusions, motion blurs, and significant…

Understanding human mobility is essential for applications ranging from urban planning to public health. Traditional mobility models such as flow networks and colocation matrices capture only pairwise interactions between discrete…

Predicting road traffic speed is a challenging task due to different types of roads, abrupt speed change and spatial dependencies between roads; it requires the modeling of dynamically changing spatial dependencies among roads and temporal…

Neural network (NN)-based methods have emerged as an attractive approach for robot motion planning due to strong learning capabilities of NN models and their inherently high parallelism. Despite the current development in this direction,…

Protective behavior exhibited by people with chronic pain (CP) during physical activities is the key to understanding their physical and emotional states. Existing automatic protective behavior detection (PBD) methods rely on…

Local features at neighboring spatial positions in feature maps have high correlation since their receptive fields are often overlapped. Self-attention usually uses the weighted sum (or other functions) with internal elements of each local…

Spatio-Temporal Graph Neural Networks (STGNNs) have emerged as a powerful tool for modeling dynamic graph-structured data across diverse domains. However, they often fail to generalize in Spatio-Temporal Out-of-Distribution (STOOD)…

Recognition of daily activities is a critical element for effective Ambient Assisted Living (AAL) systems, particularly to monitor the well-being and support the independence of older adults in indoor environments. However, developing…

Human Activity Recognition (HAR) has become increasingly popular with ubiquitous computing, driven by the popularity of wearable sensors in fields like healthcare and sports. While Convolutional Neural Networks (ConvNets) have significantly…

Objects are entities we act upon, where the functionality of an object is determined by how we interact with it. In this work we propose a Dual Attention Network model which reasons about human-object interactions. The dual-attentional…

Given trajectories with gaps, we investigate methods to tighten spatial bounds on areas (e.g., nodes in a spatial network) where possible rendezvous activity could have occurred. The problem is important for reducing the onerous amount of…

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…

In order to ensure safe autonomous driving, precise information about the conditions in and around the vehicle must be available. Accordingly, the monitoring of occupants and objects inside the vehicle is crucial. In the state-of-the-art,…

Human activity recognition (HAR) requires extracting accurate spatial-temporal features with human movements. A mmWave radar point cloud-based HAR system suffers from sparsity and variable-size problems due to the physical features of the…

Pedestrian Attribute Recognition (PAR) plays a crucial role in various vision tasks such as person retrieval and identification. Most existing attribute-based retrieval methods operate under the closed-set assumption that all attribute…