Related papers: PaStaNet: Toward Human Activity Knowledge Engine

Active Shape Model (ASM) is a statistical model of object shapes that represents a target structure. ASM can guide machine learning algorithms to fit a set of points representing an object (e.g., face) onto an image. This paper presents a…

Skeleton-based action recognition is vital for comprehending human-centric videos and has applications in diverse domains. One of the challenges of skeleton-based action recognition is dealing with low-quality data, such as skeletons that…

This paper presents the designing of a neural network for the classification of Human activity. A Triaxial accelerometer sensor, housed in a chest worn sensor unit, has been used for capturing the acceleration of the movements associated.…

Human Pose Estimation is a crucial module in human-machine interaction applications and, especially since the rise in deep learning technology, robust methods are available to consumers using RGB cameras and commercial GPUs. On the other…

The task of semi-supervised video object segmentation (VOS) has been greatly advanced and state-of-the-art performance has been made by dense matching-based methods. The recent methods leverage space-time memory (STM) networks and learn to…

We propose a method for inferring human attributes (such as gender, hair style, clothes style, expression, action) from images of people under large variation of viewpoint, pose, appearance, articulation and occlusion. Convolutional Neural…

Human action analysis and understanding in videos is an important and challenging task. Although substantial progress has been made in past years, the explainability of existing methods is still limited. In this work, we propose a novel…

Many real-world computer vision tasks, such as depth completion, must handle inputs with arbitrarily shaped regions of missing or invalid data. For Convolutional Neural Networks (CNNs), Partial Convolutions solved this by a mask-aware…

Multimodal-based action recognition methods have achieved high success using pose and RGB modality. However, skeletons sequences lack appearance depiction and RGB images suffer irrelevant noise due to modality limitations. To address this,…

Human hands, the primary means of non-verbal communication, convey intricate semantics in various scenarios. Due to the high sensitivity of individuals to hand motions, even minor errors in hand motions can significantly impact the user…

Existing AI systems for modeling human behavior operate at the level of individuals or detect events after they occur. As a result, they systematically fail to capture the collective dynamics that determine whether a group remains stable or…

This technical report introduces our 2nd place solution to Kinetics-TPS Track on Part-level Action Parsing in ICCV DeeperAction Workshop 2021. Our entry is mainly based on YOLOF for instance and part detection, HRNet for human pose…

Wearable sensor devices, which offer the advantage of recording daily objects used by a person while performing an activity, enable the feasibility of unsupervised Human Activity Recognition (HAR). Unfortunately, previous unsupervised…

Human Activity Recognition (HAR) is a key building block of many emerging applications such as intelligent mobility, sports analytics, ambient-assisted living and human-robot interaction. With robust HAR, systems will become more…

In this work, we focus on Interactive Human Parsing (IHP), which aims to segment a human image into multiple human body parts with guidance from users' interactions. This new task inherits the class-aware property of human parsing, which…

In recent years, the gap between Deep Learning (DL) methods and analytical or numerical approaches in scientific computing is tried to be filled by the evolution of Physics-Informed Neural Networks (PINNs). However, still, there are many…

Human activity recognition (HAR) in ubiquitous computing is beginning to adopt deep learning to substitute for well-established analysis techniques that rely on hand-crafted feature extraction and classification techniques. From these…

Most current action recognition methods heavily rely on appearance information by taking an RGB sequence of entire image regions as input. While being effective in exploiting contextual information around humans, e.g., human appearance and…

Existing models of human visual attention are generally unable to incorporate direct task guidance and therefore cannot model an intent or goal when exploring a scene. To integrate guidance of any downstream visual task into attention…

Significant advancements have been made in developing parametric models for digital humans, with various approaches concentrating on parts such as the human body, hand, or face. Nevertheless, connectors such as the neck have been overlooked…