相关论文: A Deeper Dive Into What Deep Spatiotemporal Networ…

With advancements in GPS, remote sensing, and computational simulation, an enormous volume of spatiotemporal data is being collected at an increasing speed from various application domains, spanning Earth sciences, agriculture, smart…

Motion Planning, as a fundamental technology of automatic navigation for the autonomous vehicle, is still an open challenging issue in the real-life traffic situation and is mostly applied by the model-based approaches. However, due to the…

Long-term complex activity recognition and localisation can be crucial for decision making in autonomous systems such as smart cars and surgical robots. Here we address the problem via a novel deformable, spatiotemporal scene graph…

Information theory and the framework of information dynamics have been used to provide tools to characterise complex systems. In particular, we are interested in quantifying information storage, information modification and information…

Classifying videos according to content semantics is an important problem with a wide range of applications. In this paper, we propose a hybrid deep learning framework for video classification, which is able to model static spatial…

Trajectory Prediction of dynamic objects is a widely studied topic in the field of artificial intelligence. Thanks to a large number of applications like predicting abnormal events, navigation system for the blind, etc. there have been many…

The role of long- and short-term dynamics towards salient object detection in videos is under-researched. We present a Transformer-based approach to learn a joint representation of video frames and past saliency information. Our model…

We propose a method for learning dynamical systems from high-dimensional empirical data that combines variational autoencoders and (spatio-)temporal attention within a framework designed to enforce certain scientifically-motivated…

Understanding how visual information is encoded in biological and artificial systems often requires vision scientists to generate appropriate stimuli to test specific hypotheses. Although deep neural network models have revolutionized the…

Decoding human activity accurately from wearable sensors can aid in applications related to healthcare and context awareness. The present approaches in this domain use recurrent and/or convolutional models to capture the spatio-temporal…

Studies of human mobility increasingly rely on digital sensing, the large-scale recording of human activity facilitated by digital technologies. Questions of variability and population representativity, however, in patterns seen from these…

In this paper, we propose to improve the traditional use of RNNs by employing a many to many model for video classification. We analyze the importance of modeling spatial layout and temporal encoding for daily living action recognition.…

Encoding a sequence of observations is an essential task with many applications. The encoding can become highly efficient when the observations are generated by a dynamical system. A dynamical system imposes regularities on the observations…

The creation of manipulated multimedia content involving human characters has reached in the last years unprecedented realism, calling for automated techniques to expose synthetically generated faces in images and videos. This work explores…

This paper provides a review on representation learning for videos. We classify recent spatiotemporal feature learning methods for sequential visual data and compare their pros and cons for general video analysis. Building effective…

We propose an online spatiotemporal articulation model estimation framework that estimates both articulated structure as well as a temporal prediction model solely using passive observations. The resulting model can predict future mo- tions…

Spatially dense self-supervised learning is a rapidly growing problem domain with promising applications for unsupervised segmentation and pretraining for dense downstream tasks. Despite the abundance of temporal data in the form of videos,…

Automated real-time prediction of the ergonomic risks of manipulating objects is a key unsolved challenge in developing effective human-robot collaboration systems for logistics and manufacturing applications. We present a foundational…

Recognizing human actions in videos requires spatial and temporal understanding. Most existing action recognition models lack a balanced spatio-temporal understanding of videos. In this work, we propose a novel two-stream architecture,…

Motions are reflected in videos as the movement of pixels, and actions are essentially patterns of inconsistent motions between the foreground and the background. To well distinguish the actions, especially those with complicated…