What is the translation of " 视觉任务 " in English?

• vision tasks
• visual tasks
• vision task

Examples of using 视觉任务 in Chinese and their translations into English

也不是所有视觉任务都会发生组合爆炸(CombinatorialExplosion)。
Not all visual missions will have a combinatorial Explosion.

Caffe在视觉任务和CNN模型方面尤其受欢迎并且表现出色。
Caffe is particularly popular and performant for vision tasks and CNN models.

神经网络已经是视觉任务的标准解决方案了。
Neural networks are already the standard solution to vision tasks.

神经网络已经成为视觉任务的标准解决方案。
Neural networks are already the standard solution to vision tasks.

或许最令人惊讶的发现在于，视觉任务性能和表现学习训练数据量(取对数)之间的关系。
Perhaps the most surprising finding is the relationship between performance on vision tasks and the amount of training data(log-scale) used for representation learning.

简介ocr，或光学字符识别，是最早的计算机视觉任务之一，因为在某些方面它不需要用到深度学习。
OCR, or optical character recognition, is one of the earliest addressed computer vision tasks, since in some aspects it does not require deep learning.

Perona教授还对研究人类如何执行视觉任务(如搜索和识别图像内容)感兴趣。
Professor Perona is also interested in studying how humans perform visual tasks, such as searching and recognizing image content.

图像分类:图像分类是一项计算机视觉任务，它让计算机识别特定的图像。
Image classification: Image classification is a computer vision task that teaches computer to recognize certain images.

组合模型的优点已经在许多视觉任务里面体现了：比如2017年登上Science的、用来识别CAPTCHA验证码的模型。
The advantages of combinatorial models have been demonstrated in many visual tasks, such as the 2017 Science model, which recognizes CAPTCHA verification codes.

深度学习在挑战性的计算机视觉任务上取得了令人印象深刻的进展，并有望取得进一步的进展。
Deep learning has made impressive inroads on challenging computer vision tasks and makes the promise of further advances.

人脸识别是一项计算机视觉任务，根据人脸的照片来识别和验证某个人。
Face recognition is a computer vision task of identifying and verifying a person based on a photograph of their face.

识别26个常见视觉任务之间的关系，如目标识别、深度估计、边缘检测和姿态估计。
Identifying relationships between 26 common visual tasks, such as object recognition, depth estimation, edge detection, and pose estimation.

机器之心：想要让一个自动驾驶系统作出正确的决策，首先要完成哪些计算机视觉任务？?
Syneced: What computer vision tasks do we need to accomplish first in order to make an automatic driving system to make the right decisions?

吴恩达非常准确地解释了很多优化计算机视觉任务需要了解的复杂概念。
Ng does an excellent job at explaining many of the complex ideas required to optimize any computer vision task.

一些结果很容易预测：在更明亮的环境中，我们更加警觉，能更好地完成视觉任务，犯更少的错误。
Research is showing that in brighter environments, we are more alert, complete visual tasks better and make fewer mistakes.

此外，我们还将讨论如何从该模型提取更高级别的特征，以重复用于其他视觉任务。
We will also discuss how to extract higher level features from this model which may be reused for other vision tasks.

大脑的“减速”最终会影响执行高级视觉任务如字母识别的能力。
The brain's“slowdown” eventually affects its ability to perform high-level visual tasks, such as letter identification.

然后，这些训练好的滤波器就可以被使用到任何其他的计算机视觉任务。
These filters can then be used in any other computer vision task.

当网络训练一组图像时，它们重新学习，这使得深度学习模型对于计算机视觉任务非常准确。
They're learned while the network trains on a set of images, which makes deep learning models extremely accurate for computer vision tasks.

Taskonomy：斯坦福大学开展的关于26项不同视觉任务之间迁移的研究。
Taskonomy: a study of transfer learning between 26 different visual tasks carried out at Stanford.

这种模型具有较高的可解释性和有效性，但在许多语言和计算机视觉任务中，却没能达到较高的准确度。
The models were highly explainable and somewhat effective but failed to reach a high accuracy in many language and computer vision tasks.

我们的第一个观察结果是大规模数据有助于表征学习，进而改善了我们研究的每个视觉任务的性能表现。
Our first observation is that large-scale data helps in representation learning which in-turn improves the performance on each vision task we study.

朱在计算神经科学领域工作，他训练计算机模型执行视觉任务，以更好地理解视觉。
Working in computational neuroscience, Zhu trains computer models to perform visual tasks to better understand vision.

经过AlexKrizhevskyImageNet网络学习的过滤器，已经被重复用在各种计算机视觉任务中，并获得了极大的成功。
The filters learned by Alex Krizhevsky's ImageNet network have been reused for various other computer vision tasks with great success.

智能传感器-一个单元，用于执行单个机器视觉任务。
Smart Sensors- A single unit that is designed to perform a single machine vision task.

我们的主要产品In-Sight®视觉系统是一种坚实耐用的工业系统，可以解决几乎任何视觉任务。
In-Sight Vision Systems Our main product range, In-Sight® vision systems are rugged, industrial systems that can solve virtually any vision task.

特别地，卷积神经网络(CNN)已经被证明是可用于许多计算机视觉任务的有利工具。
In particular, convolutional neural networks(CNNs) have proven to be powerful tools for a broad range of computer vision tasks.

本文主要聚焦于计算机视觉，因此很自然地描述了计算机视觉任务的分类。
This article is mainly focused on Computer Vision, so it is natural to describe the horizon of computer vision tasks.

我们观察到的首个现象是，大规模数据有助于表征学习，从而优化我们所研究的所有视觉任务的性能。
Our first observation is that large-scale data helps in representation learning which in-turn improves the performance on each vision task we study.