Related papers: PERF-Net: Pose Empowered RGB-Flow Net

Event-based cameras have shown great promise in a variety of situations where frame based cameras suffer, such as high speed motions and high dynamic range scenes. However, developing algorithms for event measurements requires a new class…

Good temporal representations are crucial for video understanding, and the state-of-the-art video recognition framework is based on two-stream networks. In such framework, besides the regular ConvNets responsible for RGB frame inputs, a…

Understanding accurate information on human behaviours is one of the most important tasks in machine intelligence. Human Activity Recognition that aims to understand human activities from a video is a challenging task due to various…

Future frame prediction in videos is a promising avenue for unsupervised video representation learning. Video frames are naturally generated by the inherent pixel flows from preceding frames based on the appearance and motion dynamics in…

Many semantic video analysis tasks can benefit from multiple, heterogenous signals. For example, in addition to the original RGB input sequences, sequences of optical flow are usually used to boost the performance of human action…

Multi-step prediction models, such as diffusion and rectified flow models, have emerged as state-of-the-art solutions for generation tasks. However, these models exhibit higher latency in sampling new frames compared to single-step methods.…

In this paper we address the problem of human action recognition from video sequences. Inspired by the exemplary results obtained via automatic feature learning and deep learning approaches in computer vision, we focus our attention towards…

Event cameras offer promising properties, such as high temporal resolution and high dynamic range. These benefits have been utilized into many machine vision tasks, especially optical flow estimation. Currently, most existing event-based…

This paper proposes a novel system to estimate and track the 3D poses of multiple persons in calibrated RGB-Depth camera networks. The multi-view 3D pose of each person is computed by a central node which receives the single-view outcomes…

In this paper, we propose the use of a semantic image, an improved representation for video analysis, principally in combination with Inception networks. The semantic image is obtained by applying localized sparse segmentation using global…

We present a deep learning-based multitask framework for joint 3D human pose estimation and action recognition from RGB video sequences. Our approach proceeds along two stages. In the first, we run a real-time 2D pose detector to determine…

To address the problem of training on small datasets for action recognition tasks, most prior works are either based on a large number of training samples or require pre-trained models transferred from other large datasets to tackle…

Understanding continuous video streams plays a fundamental role in real-time applications including embodied AI and autonomous driving. Unlike offline video understanding, streaming video understanding requires the ability to process video…

This paper considers to jointly tackle the highly correlated tasks of estimating 3D human body poses and predicting future 3D motions from RGB image sequences. Based on Lie algebra pose representation, a novel self-projection mechanism is…

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…

We consider the problem of human pose estimation. While much recent work has focused on the RGB domain, these techniques are inherently under-constrained since there can be many 3D configurations that explain the same 2D projection. To this…

We propose an approach to generate images of people given a desired appearance and pose. Disentangled representations of pose and appearance are necessary to handle the compound variability in the resulting generated images. Hence, we…

Upsampling videos of human activity is an interesting yet challenging task with many potential applications ranging from gaming to entertainment and sports broadcasting. The main difficulty in synthesizing video frames in this setting stems…

Event cameras are novel sensors that report brightness changes in the form of a stream of asynchronous "events" instead of intensity frames. They offer significant advantages with respect to conventional cameras: high temporal resolution,…

We present HumanNeRF-SE, a simple yet effective method that synthesizes diverse novel pose images with simple input. Previous HumanNeRF works require a large number of optimizable parameters to fit the human images. Instead, we reload these…