Related papers: Heatmap Pooling Network for Action Recognition fro…

Given a video and a linguistic query, video moment retrieval and highlight detection (MR&HD) aim to locate all the relevant spans while simultaneously predicting saliency scores. Most existing methods utilize RGB images as input,…

Action recognition is an open and challenging problem in computer vision. While current state-of-the-art models offer excellent recognition results, their computational expense limits their impact for many real-world applications. In this…

Action recognition, early prediction, and online action detection are complementary disciplines that are often studied independently. Most online action detection networks use a pre-trained feature extractor, which might not be optimal for…

Deep neural network is an effective choice to automatically recognize human actions utilizing data from various wearable sensors. These networks automate the process of feature extraction relying completely on data. However, various noises…

The use of RGB-D information for salient object detection has been extensively explored in recent years. However, relatively few efforts have been put towards modeling salient object detection in real-world human activity scenes with RGBD.…

This paper investigates how to perform robust visual tracking in adverse and challenging conditions using complementary visual and thermal infrared data (RGBT tracking). We propose a novel deep network architecture called qualityaware…

This work targets human action recognition in video. While recent methods typically represent actions by statistics of local video features, here we argue for the importance of a representation derived from human pose. To this end we…

The robust recognition and assessment of human actions are crucial in human-robot interaction (HRI) domains. While state-of-the-art models of action perception show remarkable results in large-scale action datasets, they mostly lack the…

Most popular deep models for action recognition in videos generate independent predictions for short clips, which are then pooled heuristically to assign an action label to the full video segment. As not all frames may characterize the…

In this paper, we introduce Coarse-Fine Networks, a two-stream architecture which benefits from different abstractions of temporal resolution to learn better video representations for long-term motion. Traditional Video models process…

We present Relightable Holoported Characters (RHC), a novel person-specific method for free-view rendering and relighting of full-body and highly dynamic humans solely observed from sparse-view RGB videos at inference. In contrast to…

Understanding the relationship between different parts of an image is crucial in a variety of applications, including object recognition, scene understanding, and image classification. Despite the fact that Convolutional Neural Networks…

Since Convolutional Neural Networks (ConvNets) are able to simultaneously learn features and classifiers to discriminate different categories of activities, recent works have employed ConvNets approaches to perform human activity…

Action parsing in videos with complex scenes is an interesting but challenging task in computer vision. In this paper, we propose a generic 3D convolutional neural network in a multi-task learning manner for effective Deep Action Parsing…

Real-time 6D object pose estimation is essential for many real-world applications, such as robotic grasping and augmented reality. To achieve an accurate object pose estimation from RGB images in real-time, we propose an effective and…

Data-fusion networks have shown significant promise for RGB-thermal scene parsing. However, the majority of existing studies have relied on symmetric duplex encoders for heterogeneous feature extraction and fusion, paying inadequate…

Detecting and recognizing human action in videos with crowded scenes is a challenging problem due to the complex environment and diversity events. Prior works always fail to deal with this problem in two aspects: (1) lacking utilizing…

Activity recognition using built-in sensors in smart and wearable devices provides great opportunities to understand and detect human behavior in the wild and gives a more holistic view of individuals' health and well being. Numerous…

Existing methods in video action recognition mostly do not distinguish human body from the environment and easily overfit the scenes and objects. In this work, we present a conceptually simple, general and high-performance framework for…

Human activity recognition (HAR) is fundamental in human-robot collaboration (HRC), enabling robots to respond to and dynamically adapt to human intentions. This paper introduces a HAR system combining a modular data glove equipped with…