相关论文: An End-to-End Two-Stream Network Based on RGB Flow…

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…

The optical flow of humans is well known to be useful for the analysis of human action. Given this, we devise an optical flow algorithm specifically for human motion and show that it is superior to generic flow methods. Designing a method…

Recent learning-based methods for event-based optical flow estimation utilize cost volumes for pixel matching but suffer from redundant computations and limited scalability to higher resolutions for flow refinement. In this work, we take…

In the domain of computer vision, optical flow stands as a cornerstone for unraveling dynamic visual scenes. However, the challenge of accurately estimating optical flow under conditions of large nonlinear motion patterns remains an open…

In this paper, we propose a new approach to under-stand actions in egocentric videos that exploits the semantics of object interactions at both frame and temporal levels. At the frame level, we use a region-based approach that takes as…

As in many other different fields, deep learning has become the main approach in most computer vision applications, such as scene understanding, object recognition, computer-human interaction or human action recognition (HAR). Research…

Two optical flow estimation problems are addressed: i) occlusion estimation and handling, and ii) estimation from image sequences longer than two frames. The proposed ContinualFlow method estimates occlusions before flow, avoiding the use…

A deep neural network has been successfully applied to an electroencephalogram (EEG)-based brain-computer interface. However, in most studies, the correlation between EEG channels and inter-region relationships are not well utilized,…

Egocentric gesture recognition is a pivotal technology for enhancing natural human-computer interaction, yet traditional RGB-based solutions suffer from motion blur and illumination variations in dynamic scenarios. While event cameras show…

We focus on the word-level visual lipreading, which requires recognizing the word being spoken, given only the video but not the audio. State-of-the-art methods explore the use of end-to-end neural networks, including a shallow (up to three…

Real-time traffic flow prediction holds significant importance within the domain of Intelligent Transportation Systems (ITS). The task of achieving a balance between prediction precision and computational efficiency presents a significant…

With recent advances in RGB-D sensing technologies as well as improvements in machine learning and fusion techniques, RGB-D facial recognition has become an active area of research. A novel attention aware method is proposed to fuse two…

Infrared (IR) imaging has the potential to enable more robust action recognition systems compared to visible spectrum cameras due to lower sensitivity to lighting conditions and appearance variability. While the action recognition task on…

One of the challenges encountered by computational simulations at exascale is the reliability of simulations in the face of hardware and software faults. These faults, expected to increase with the complexity of the computational systems,…

Discriminative correlation filters (DCF) with deep convolutional features have achieved favorable performance in recent tracking benchmarks. However, most of existing DCF trackers only consider appearance features of current frame, and…

Most existing Convolutional Neural Networks(CNNs) used for action recognition are either difficult to optimize or underuse crucial temporal information. Inspired by the fact that the recurrent model consistently makes breakthroughs in the…

We demonstrate how deep convolutional neural networks can be trained to predict 2+1 D hydrodynamic simulation results for flow coefficients, mean-transverse-momentum and charged particle multiplicity from the initial energy density profile.…

Motion is a dominant cue in automated driving systems. Optical flow is typically computed to detect moving objects and to estimate depth using triangulation. In this paper, our motivation is to leverage the existing dense optical flow to…

Diffusion models can learn rich representations during data generation, showing potential for Self-Supervised Learning (SSL), but they face a trade-off between generative quality and discriminative performance. Their iterative sampling also…

We focus on a convolutional neural network (CNN), which has recently been utilized for fluid flow analyses, from the perspective on the influence of various operations inside it by considering some canonical regression problems with fluid…