Related papers: PKU-MMD: A Large Scale Benchmark for Continuous Mu…
Vision-based human activity recognition has emerged as one of the essential research areas in video analytics domain. Over the last decade, numerous advanced deep learning algorithms have been introduced to recognize complex human actions…
Automatic human action recognition is indispensable for almost artificial intelligent systems such as video surveillance, human-computer interfaces, video retrieval, etc. Despite a lot of progress, recognizing actions in an unknown video is…
Widely shared videos on the internet are often edited. Recently, although Video Large Language Models (Vid-LLMs) have made great progress in general video understanding tasks, their capabilities in video editing understanding (VEU) tasks…
Detecting hand actions in videos is crucial for understanding video content and has diverse real-world applications. Existing approaches often focus on whole-body actions or coarse-grained action categories, lacking fine-grained hand-action…
Viewpoint change invariance and action temporal consistency are critical aspects for the effective deployment of human action detection of untrimmed videos. Existing appearance-based video detection methods often struggle with limited…
Action recognition, which is formulated as a task to identify various human actions in a video, has attracted increasing interest from computer vision researchers due to its importance in various applications. Recently, appearance-based…
To enable machines to understand the way humans interact with the physical world in daily life, 3D interaction signals should be captured in natural settings, allowing people to engage with multiple objects in a range of sequential and…
In online action detection, the goal is to detect the start of an action in a video stream as soon as it happens. For instance, if a child is chasing a ball, an autonomous car should recognize what is going on and respond immediately. This…
Visual-based human action recognition can be found in various application fields, e.g., surveillance systems, sports analytics, medical assistive technologies, or human-robot interaction frameworks, and it concerns the identification and…
The development of robust, generalized models in human activity recognition (HAR) has been hindered by the scarcity of large-scale, labeled data sets. Recent work has shown that virtual IMU data extracted from videos using computer vision…
AI-based motion capture is an emerging technology that offers a cost-effective alternative to traditional motion capture systems. However, current AI motion capture methods rely entirely on observed video sequences, similar to conventional…
Video is a promising source of knowledge for embodied agents to learn models of the world's dynamics. Large deep networks have become increasingly effective at modeling complex video data in a self-supervised manner, as evaluated by metrics…
We introduce HUMAN4D, a large and multimodal 4D dataset that contains a variety of human activities simultaneously captured by a professional marker-based MoCap, a volumetric capture and an audio recording system. By capturing 2 female and…
This paper presents a novel approach for automatic recognition of human activities for video surveillance applications. We propose to represent an activity by a combination of category components, and demonstrate that this approach offers…
We propose a new task of unsupervised action detection by action matching. Given two long videos, the objective is to temporally detect all pairs of matching video segments. A pair of video segments are matched if they share the same human…
Numerous methods for human activity recognition have been proposed in the past two decades. Many of these methods are based on sparse representation, which describes the whole video content by a set of local features. Trajectories, being…
Human activity recognition (HAR) is often limited by the scarcity of labeled datasets due to the high cost and complexity of real-world data collection. To mitigate this, recent work has explored generating virtual inertial measurement unit…
Human action recognition has been one of the most active fields of research in computer vision for last years. Two dimensional action recognition methods are facing serious challenges such as occlusion and missing the third dimension of…
In 3D action recognition, there exists rich complementary information between skeleton modalities. Nevertheless, how to model and utilize this information remains a challenging problem for self-supervised 3D action representation learning.…
We introduce a new benchmark, TAPVid-3D, for evaluating the task of long-range Tracking Any Point in 3D (TAP-3D). While point tracking in two dimensions (TAP) has many benchmarks measuring performance on real-world videos, such as…