五月的第一周过去了,盘点本周新出开源代码,希望对你有用。
目标检测
[1]Streaming Object Detection for 3-D Point Clouds
3-D点云的流目标检测
作者|Wei Han, Zhengdong Zhang, Benjamin Caine, Brandon Yang, Christoph Sprunk,
Ouais Alsharif, Jiquan Ngiam, Vijay Vasudevan, Jonathon Shlens, Zhifeng Chen
单位|Waymo;谷歌大脑
论文|https://arxiv.org/abs/2005.01864
代码|http://github.com/tensorflow/lingvo
[2]CVPR2020|Scale-Equalizing Pyramid Convolution for Object Detection
用于目标检测的尺度均衡金字塔卷积
作者|Xinjiang Wang, Shilong Zhang, Zhuoran Yu, Litong Feng, Wayne Zhang
单位|商汤
论文|https://arxiv.org/abs/2005.03101
代码|https://github.com/jshilong/SEPC
[3]Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation
增强模型学习和推理中的几何因子用于目标检测和实例分割
作者|Zhaohui Zheng, Ping Wang, Dongwei Ren, Wei Liu, Rongguang Ye, Qinghua Hu, Wangmeng Zuo
单位|哈尔滨工业大学;天津大学
论文|https://arxiv.org/abs/2005.03572
代码|https://github.com/Zzh-tju/CIoU
图像检索
[4]PyRetri: A PyTorch-based Library for Unsupervised Image Retrieval by Deep Convolutional Neural Networks
PyRetri:基于PyTorch的深度卷积神经网络无监督图像检索库
作者|Benyi Hu, Ren-Jie Song, Xiu-Shen Wei, Yazhou Yao, Xian-Sheng Hua, Yuehu Liu
单位|旷视科技;西交;南理工;阿里
论文|https://arxiv.org/abs/2005.02154
代码|https://github.com/PyRetri/PyRetri
手势识别数据集
[5]IPN Hand: A Video Dataset and Benchmark for Real-Time Continuous Hand Gesture Recognition
IPN Hand: 实时连续手势识别的视频数据集和基准测试
作者|Gibran Benitez-Garcia, Jesus Olivares-Mercado, Gabriel Sanchez-Perez, Keiji Yanai
单位|日本电子通信大学
论文|https://arxiv.org/abs/2005.02134
代码|https://github.com/GibranBenitez/IPN-hand(即将开源)
网络剪枝
[6]CVPR2020 Oral|DMCP: Differentiable Markov Channel Pruning for Neural Networks
DMCP:神经网络的可微马尔可夫通道剪枝
作者|Shaopeng Guo, Yujie Wang, Quanquan Li, Junjie Yan
单位|商汤
论文|https://arxiv.org/abs/2005.03354
代码|https://github.com/zx55/dmcp(尚未开源)
医学影像
[7]CovidCTNet: An Open-Source Deep Learning Approach to Identify Covid-19 Using CT Image
CovidCTNet:一种使用CT图像识别Covid-19的开源深度学习方法
作者|Tahereh Javaheri, Morteza Homayounfar, Zohreh Amoozgar, Reza Reiazi, Fatemeh Homayounieh, Engy Abbas, Azadeh Laali, Amir Reza Radmard, Mohammad Hadi Gharib, Seyed Ali Javad Mousavi,
Omid Ghaemi, Rosa Babaei, Hadi Karimi Mobin, Mehdi Hosseinzadeh, Rana Jahanban-Esfahlan, Khaled Seidi, Mannudeep K. Kalra,Guanglan Zhang, L.T. Chitkushev, Benjamin Haibe-Kains,Reza Malekzadeh, Reza Rawassizadeh
单位|波士顿大学;伊朗医科大学;哈佛医学院;多伦多大学
论文|https://arxiv.org/abs/2005.03059
代码|https://gitlab.com/users/sign_in
[8]AlignShift: Bridging the Gap of Imaging Thickness in 3D Anisotropic Volumes
作者|Jiancheng Yang, Yi He, Xiaoyang Huang, Jingwei Xu, Xiaodan Ye, Guangyu Tao, Bingbing Ni
单位|戴安娜技术;上海交通;华为海思
论文|https://arxiv.org/abs/2005.01969
代码|https://github.com/M3DV/
AlignShift(404)
视觉语言导航
[9]IJCAI 2020|Diagnosing the Environment Bias in Vision-and-Language Navigation
视觉语言导航中的环境偏差诊断
作者|Yubo Zhang, Hao Tan, Mohit Bansal
论文|https://arxiv.org/abs/2005.03086
代码|https://github.com/zhangybzbo/
EnvBiasVLN
深度学习训练
[10]IMPORTANCE OF DATA LOADING PIPELINE IN TRAINING DEEP NEURAL NETWORKS
数据加载管道在深度神经网络训练中的重要性
作者|Mahdi Zolnouri, Xinlin Li, Vahid Partovi Nia
单位|华为诺亚方舟实验室
论文|https://arxiv.org/abs/2005.02130
代码|https://github.com/NVIDIA/DALI
[11]ICLR2020|Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation
通过混合转换和峰值定时相关的反向传播来启用深度峰值神经网络
作者|Nitin Rathi, Gopalakrishnan Srinivasan, Priyadarshini Panda, Kaushik Roy
单位|普渡大学;耶鲁
论文|https://arxiv.org/abs/2005.01807
代码|https://github.com/nitin-rathi/hybrid-snn-conversion
视频动作分析
[12]Adaptive Interaction Modeling via Graph Operations Search
基于图运算搜索的自适应交互建模
作者|Haoxin Li, Wei-Shi Zheng, Yu Tao, Haifeng Hu, Jian-Huang Lai
单位|中山大学;鹏程实验室
论文|https://arxiv.org/abs/2005.02113
代码|https://github.com/lihaoxin05/graph-operations-search
智能交通
[13]HOG, LBP and SVM based Traf ic Density Estimation at Interp
基于HOG、LBP和SVM的交叉口交通流密度估计
作者|Devashish Prasad, Kshitij Kapadni, Ayan Gadpal, Manish Visave, Kavita Sultanpure
单位|印度普纳计算机技术研究所
论文|https://arxiv.org/abs/2005.01770
代码|https://github.com/DevashishPrasad/
Smart-Traffic-Junction
图像分割
[14]CVPR2020|CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement
CascadePSP:通过全局和局部优化实现与类无关和超高分辨率的分割
作者|Ho Kei Cheng (HKUST), Jihoon Chung (HKUST), Yu-Wing Tai (Tencent), Chi-Keung Tang (HKUST)
单位|香港科技大学;腾讯
论文|https://arxiv.org/abs/2005.02551
代码|https://github.com/hkchengrex/
CascadePSP
对抗学习
[15]CVPR2020|Enhancing Intrinsic Adversarial Robustness via Feature Pyramid Decoder
利用特征金字塔解码器增强内在对抗性鲁棒性研究
作者|Guanlin Li, Shuya Ding, Jun Luo, Chang Liu
单位|南洋理工大学
论文|https://arxiv.org/abs/2005.02552
代码|https://github.com/GuanlinLee/FPD-for-
Adversarial-Robustness
多媒体事件提取
[16]ACL 2020oral|Cross-media Structured Common Space for Multimedia Event Extraction
用于多媒体事件提取的跨媒体结构化公共空间
作者|Manling Li, Alireza Zareian, Qi Zeng, Spencer Whitehead, Di Lu, Heng Ji, Shih-Fu Chang
单位|哥伦比亚大学;伊利诺伊大学香槟分校
论文|https://arxiv.org/abs/2005.02472
代码|http://blender.cs.illinois.edu/software/
m2e2/
奖励学习
[17]Active Preference-Based Gaussian Process Regression for Reward Learning
基于主动偏好的高斯过程回归模型在奖励学习中的应用
作者|Erdem Bıyık, Nicolas Huynh, Mykel J. Kochenderfer, Dorsa Sadigh
单位|洛桑联邦理工学院;斯坦福大学
论文|https://arxiv.org/abs/2005.02575
代码|https://github.com/Stanford-ILIAD/active-preference-based-gpr
数据增强
[18]Designing Data Augmentation for Simulating Interventions
模拟干预的数据增强设计
作者|Maximilian Ilse, Jakub M. Tomczak, Patrick Forré
单位|阿姆斯特丹大学
论文|https://arxiv.org/abs/2005.01856
代码|https://github.com/AMLab-Amsterdam/DataAugmentationInterventions
点云识别与处理
[19]CVPR 2020|From Image Collections to Point Clouds with Self-supervised Shape and Pose Networks
自监督形状和姿态网络的3D重建
作者|K L Navaneet, Ansu Mathew, Shashank Kashyap, Wei-Chih Hung, Varun Jampani, R. Venkatesh Babu
单位|印度科学研究所;谷歌研究;加州大学
论文|https://arxiv.org/abs/2005.01939
代码|https://github.com/val-iisc/ssl_3d_recon
论文下载:
在我爱计算机视觉公众号对话框回复“200501”即可获取以上所有论文下载地址。
END
备注如:目标检测
CV细分交流群
专业包括目标检测、目标跟踪、图像增强、强化学习、模型压缩、视频理解、人脸技术、三维视觉、SLAM、GAN、GNN等,
若已为CV君其他账号好友请直接私信。
我爱计算机视觉
微信号:aicvml
QQ群:805388940
微博知乎:@我爱计算机视觉
网站:www.52cv.net
在看,让更多人看到