Related papers: A Short Note on the Kinetics-700-2020 Human Action…
Due to the statistical complexity of video, the high degree of inherent stochasticity, and the sheer amount of data, generating natural video remains a challenging task. State-of-the-art video generation models often attempt to address…
Annotating camera poses on dynamic Internet videos at scale is critical for advancing fields like realistic video generation and simulation. However, collecting such a dataset is difficult, as most Internet videos are unsuitable for pose…
In recent years, automatic video caption generation has attracted considerable attention. This paper focuses on the generation of Japanese captions for describing human actions. While most currently available video caption datasets have…
Multimodal summarization with multimodal output (MSMO) has emerged as a promising research direction. Nonetheless, numerous limitations exist within existing public MSMO datasets, including insufficient maintenance, data inaccessibility,…
Learning text-video embeddings usually requires a dataset of video clips with manually provided captions. However, such datasets are expensive and time consuming to create and therefore difficult to obtain on a large scale. In this work, we…
The study of complex human interactions and group activities has become a focal point in human-centric computer vision. However, progress in related tasks is often hindered by the challenges of obtaining large-scale labeled datasets from…
Action recognition based on skeleton data has recently witnessed increasing attention and progress. State-of-the-art approaches adopting Graph Convolutional networks (GCNs) can effectively extract features on human skeletons relying on the…
Human action recognition from RGB-D (Red, Green, Blue and Depth) data has attracted increasing attention since the first work reported in 2010. Over this period, many benchmark datasets have been created to facilitate the development and…
While automatic monitoring and coaching of exercises are showing encouraging results in non-medical applications, they still have limitations such as errors and limited use contexts. To allow the development and assessment of physical…
This paper proposes a new 3D Human Action Recognition system as a two-phase system: (1) Deep Metric Learning Module which learns a similarity metric between two 3D joint sequences using Siamese-LSTM networks; (2) A Multiclass Classification…
Understanding animals' behaviors is significant for a wide range of applications. However, existing animal behavior datasets have limitations in multiple aspects, including limited numbers of animal classes, data samples and provided tasks,…
MVImgNet is a large-scale dataset that contains multi-view images of ~220k real-world objects in 238 classes. As a counterpart of ImageNet, it introduces 3D visual signals via multi-view shooting, making a soft bridge between 2D and 3D…
Recognizing human actions in untrimmed videos is an important challenging task. An effective 3D motion representation and a powerful learning model are two key factors influencing recognition performance. In this paper we introduce a new…
An automatic gun detection system can detect potential gun-related violence at an early stage that is of paramount importance for citizens security. In the whole system, object detection algorithm is the key to perceive the environment so…
360{\deg} videos in recent years have experienced booming development. Compared to traditional videos, 360{\deg} videos are featured with uncertain user behaviors, bringing opportunities as well as challenges. Datasets are necessary for…
3D human motion prediction, predicting future poses from a given sequence, is an issue of great significance and challenge in computer vision and machine intelligence, which can help machines in understanding human behaviors. Due to the…
We consider predicting the user's head motion in 360-degree videos, with 2 modalities only: the past user's positions and the video content (not knowing other users' traces). We make two main contributions. First, we re-examine existing…
In this work, we propose Knowledge Integration Networks (referred as KINet) for video action recognition. KINet is capable of aggregating meaningful context features which are of great importance to identifying an action, such as human…
We present a bundle-adjustment-based algorithm for recovering accurate 3D human pose and meshes from monocular videos. Unlike previous algorithms which operate on single frames, we show that reconstructing a person over an entire sequence…
The problem of task planning for artificial agents remains largely unsolved. While there has been increasing interest in data-driven approaches for the study of task planning for artificial agents, a significant remaining bottleneck is the…