人工智能培训

搜索

论文代码开源:评估句子矢量表示中的构图(Assessing Composition in Sentence Vector Representations)

[复制链接]
admin 发表于 2018-9-15 10:03:51 | 显示全部楼层 |阅读模式
admin 2018-9-15 10:03:51 624 0 显示全部楼层
人工智能论文代码开源:评估句子矢量表示中的构图(Assessing Composition in Sentence Vector Representations)请注意该人工智能论文代码开源在github,大部分是python写的,框架可能是tensorflow或者pytorch。在线多目标跟踪是时间关键型视频分析应用中的基本问题。流行的逐个检测框架的一个主要挑战是如何将不可靠的检测结果与现有的跟踪相关联。在本文中,我们建议通过从检测和跟踪的输出中收集候选来处理不可靠的检测。生成冗余候选者背后的直觉是检测和跟踪可以在不同场景中补充其他。高可信度的检测结果预防长期漂移,并且轨道的预测可以处理由遮挡引起的噪声检测。为了实时地从可合理数量的候选者中应用最佳选择,我们提出了一种基于完全卷积神经网络的新型评分函数,其在整个图像上共享大多数计算。此外,我们采用深度学习的外观表示,在大型人格识别数据集上进行训练,以提高ourtracker的识别能力。大量实验表明,我们的跟踪器可以在广泛使用的人员跟踪基准测试中实现实时和最先进的性能。
Online multi-object tracking is a fundamental problem in time-critical videoanalysis applications.A major challenge in the popular tracking-by-detectionframework is how to associate unreliable detection results with existingtracks.In this paper, we propose to handle unreliable detection by collectingcandidates from outputs of both detection and tracking.The intuition behindgenerating redundant candidates is that detection and tracks can complementeach other in different scenarios.Detection results of high confidence preventtracking drifts in the long term, and predictions of tracks can handle noisydetection caused by occlusion.In order to apply optimal selection from aconsiderable amount of candidates in real-time, we present a novel scoringfunction based on a fully convolutional neural network, that shares mostcomputations on the entire image.Moreover, we adopt a deeply learnedappearance representation, which is trained on large-scale personre-identification datasets, to improve the identification ability of ourtracker.Extensive experiments show that our tracker achieves real-time andstate-of-the-art performance on a widely used people tracking benchmark.论文代码开源:评估句子矢量表示中的构图(Assessing Composition in Sentence Vector Representations) MSu2SAwSisxSA2pW.jpg
URL地址:https://arxiv.org/abs/1809.04427v1     ----pdf下载地址:https://arxiv.org/pdf/1809.04427v1    ----         ----github下载地址:https://github.com/longcw/MOTDT    ----    论文代码开源:评估句子矢量表示中的构图(Assessing Composition in Sentence Vector Representations)请注意该人工智能论文代码开源在github,大部分是python写的,框架可能是tensorflow或者pytorch,keras,至于具体是哪一个没有完全测试。
回复

使用道具 举报

您需要登录后才可以回帖 登录 | 立即注册

本版积分规则 返回列表 发新帖

admin当前离线
管理员

查看:624 | 回复:0

快速回复 返回顶部 返回列表