ICCV2017论文分类

最新推荐文章于 2025-07-11 16:00:26 发布

迷川浩浩_ZJU

最新推荐文章于 2025-07-11 16:00:26 发布

阅读量6.2k

点赞数 2

CC 4.0 BY-SA版权

分类专栏：深度学习

本文链接：https://blog.youkuaiyun.com/qq_21190081/article/details/78493773

本文详细介绍了ICCV2017中涉及的多个计算机视觉领域的研究，包括Person ReID、跟踪、姿势估计、语义分割、实例分割、人群计数、车辆重识别以及GAN的应用。在Person ReID中，探讨了不同的深度学习方法，如神经人搜索机器和视差对称度量学习。在跟踪领域，提出了基于CNN的单目标跟踪器与空间时间注意力机制。同时，还深入研究了姿势估计，利用深度学习进行3D人体姿态估计。此外，还涵盖了视频语义分割、实例分割以及GAN在生成无监督样本和图像到图像转换中的应用。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Person ReID

Neural Person Search Machines
Cross-View Asymmetric Metric Learning for Unsupervised Person Re-Identification
SHaPE: A Novel Graph Theoretic Algorithm for Making Consensus-Based Decisions in Person Re-Identification Systems
A Two Stream Siamese Convolutional Neural Network for Person Re-Identification
Efficient Online Local Metric Adaptation via Negative Samples for Person Re-Identification
Learning View-Invariant Features for Person Identification in Temporally Synchronized Videos Taken by Wearable Cameras
Deeply-Learned Part-Aligned Representations for Person Re-Identification
Unlabeled Samples Generated by GAN Improve the Person Re-Identification Baseline in Vitro
Pose-Driven Deep Convolutional Model for Person Re-Identification
Jointly Attentive Spatial-Temporal Pooling Networks for Video-Based Person Re-Identification
RGB-Infrared Cross-Modality Person Re-Identification
Multi-Scale Deep Learning Architectures for Person Re-Identification