PG-Net: Pixel to Global Matching Network for Visual Tracking作者 | Bingyan Liao, Chenye Wang, Yayun Wang, Yaonong Wang, Jun Yin单位 | 浙江大华技术股份有限公司论文 | https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123670426.pdf备注 | ECCV 2020
CLNet: A Compact Latent Network for Fast Adjusting Siamese Trackers作者 | Xingping Dong, Jianbing Shen, Ling Shao, Fatih Porikli单位 | Inception Institute of Artificial Intelligence;Mohamed bin Zayed University of Artificial Intelligence;Australian National University论文 | https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123650375.pdf代码 | https://github.com/xingpingdong/CLNet-tracking备注 | ECCV 2020
Learning Feature Embeddings for Discriminant Model based Tracking作者 | Linyu Zheng, Ming Tang, Yingying Chen, Jinqiao Wang, Hanqing Lu单位 | 中科院;国科大;深圳英飞拓科技股份有限公司;ObjectEye Inc论文 | https://arxiv.org/abs/1906.10414代码 | https://github.com/noneUmbrella/DCFST备注 | ECCV 2020
Object Tracking using Spatio-Temporal Networks for Future Prediction Location作者 | Yuan Liu, Ruoteng Li, Yu Cheng, Robby T. Tan, Xiubao Sui单位 | 南京理工大学;新加坡国立大学;耶鲁-新加坡国立大学学院论文 | https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123670001.pdf备注 | ECCV 2020利用 Spatio-Temporal 网络进行目标跟踪,实现未来的预测定位。
Know Your Surroundings: Exploiting Scene Information for Object Tracking作者 | Goutam Bhat, Martin Danelljan, Luc Van Gool, Radu Timofte单位 | 苏黎世联邦理工学院论文 | https://arxiv.org/abs/2003.11014备注 | ECCV 2020利用场景信息用于目标跟踪,所提出的方法在3个跟踪基准上创造了新SOTA,在最近的GOT-10k数据集上实现了63.6%的AO得分。
Tracking Emerges by Looking Around Static Scenes, with Neural 3D Mapping作者 | Adam W. Harley, Shrinidhi K. Lakshmikanth, Paul Schydlo, Katerina Fragkiadaki单位 | 卡内基梅隆大学论文 | https://arxiv.org/abs/2008.01295代码 | https://github.com/aharley/neural_3d_tracking(未开源)备注 | ECCV 2020通过观察静态场景,跟踪出现的新来目标。
RGBT 跟踪
Challenge-Aware RGBT Tracking作者 | Chenglong Li, Lei Liu, Andong Lu, Qing Ji, Jin Tang单位 | 安徽大学论文 | https://arxiv.org/abs/2007.13143备注 | ECCV 2020RGB与热源信号的目标跟踪。
Deep Learning-based Pupil Center Detection for Fast and Accurate Eye Tracking System作者 | Kang Il Lee, Jung Ho Jeon, Byung Cheol Song单位 | 韩国仁荷大学论文 | https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123640035.pdf备注 | ECCV 2020所提出的系统不仅在通用计算机环境下可达到52 FPS,而且在BioID、GI4E和Talking Face Video数据集的精细度精度方面分别达到96.71%、99.84%和96.38%。视频丨https://v.qq.com/x/page/y3152g4y78s.html
对抗学习+目标跟踪
SPARK: Spatial-aware Online Incremental Attack Against Visual Tracking作者 | Qing Guo, Xiaofei Xie, Felix Juefei-Xu, Lei Ma, Zhongguo Li, Wanli Xue, Wei Feng, Yang Liu单位 | 天津大学;南洋理工大学;阿里;Kyushu University;天津理工大学论文 | https://arxiv.org/abs/1910.08681备注 | ECCV 2020