Related papers: Prompt-guided Disentangled Representation for Acti…
Action recognition in videos has attracted a lot of attention in the past decade. In order to learn robust models, previous methods usually assume videos are trimmed as short sequences and require ground-truth annotations of each video…
Though action recognition in videos has achieved great success recently, it remains a challenging task due to the massive computational cost. Designing lightweight networks is a possible solution, but it may degrade the recognition…
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…
This paper presents a survey of human action recognition approaches based on visual data recorded from a single video camera. We propose an organizing framework which puts in evidence the evolution of the area, with techniques moving from…
Early action recognition is an important and challenging problem that enables the recognition of an action from a partially observed video stream where the activity is potentially unfinished or even not started. In this work, we propose a…
A dominant paradigm for learning-based approaches in computer vision is training generic models, such as ResNet for image recognition, or I3D for video understanding, on large datasets and allowing them to discover the optimal…
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…
Dynamic graph neural networks (DyGNNs) have demonstrated powerful predictive abilities by exploiting graph structural and temporal dynamics. However, the existing DyGNNs fail to handle distribution shifts, which naturally exist in dynamic…
Spatial-temporal graphs have been widely used by skeleton-based action recognition algorithms to model human action dynamics. To capture robust movement patterns from these graphs, long-range and multi-scale context aggregation and…
Recent video action recognition methods have shown excellent performance by adapting large-scale pre-trained language-image models to the video domain. However, language models contain rich common sense priors - the scene contexts that…
In this paper, we are interested in self-supervised learning the motion cues in videos using dynamic motion filters for a better motion representation to finally boost human action recognition in particular. Thus far, the vision community…
With the explosive growth of video data in real-world applications, a comprehensive representation of videos becomes increasingly important. In this paper, we address the problem of video scene recognition, whose goal is to learn a…
Static image action recognition, which aims to recognize action based on a single image, usually relies on expensive human labeling effort such as adequate labeled action images and large-scale labeled image dataset. In contrast, abundant…
Capturing scene dynamics and predicting the future scene state is challenging but essential for robotic manipulation tasks, especially when the scene contains both rigid and deformable objects. In this work, we contribute a simulation…
Document Presentation Attack Detection (DPAD) is an important measure in protecting the authenticity of a document image. However, recent DPAD methods demand additional resources, such as manual effort in collecting additional data or…
Advanced driver assistance and automated driving systems rely on risk estimation modules to predict and avoid dangerous situations. Current methods use expensive sensor setups and complex processing pipeline, limiting their availability and…
Dynamic Mode Decomposition (DMD) is a numerical method that seeks to fit timeseries data to a linear dynamical system. In doing so, DMD decomposes dynamic data into spatially coherent modes that evolve in time according to exponential…
This paper studies how to introduce viewpoint-invariant feature representations that can help action recognition and detection. Although we have witnessed great progress of action recognition in the past decade, it remains challenging yet…
Human actions recognition is a fundamental task in artificial vision, that has earned a great importance in recent years due to its multiple applications in different areas. %, such as the study of human behavior, security or video…
We introduce the concept of "dynamic image", a novel compact representation of videos useful for video analysis, particularly in combination with convolutional neural networks (CNNs). A dynamic image encodes temporal data such as RGB or…