Skip to content

Commit 68595c8

Browse files
amusiamusi
committed
Update(20190408)：添加6篇论文（目标跟踪、GAN、6DoF姿态估计等方向）
1 parent 5d7a8e5 commit 68595c8

File tree

1 file changed

+76
-17
lines changed

1 file changed

+76
-17
lines changed

‎README.md

Lines changed: 76 additions & 17 deletions
Original file line numberDiff line numberDiff line change
@@ -6,80 +6,139 @@ CVPR 2019 论文开源项目合集
66
- [目标跟踪](#Object-Tracking)
77
- [语义分割](#Semantic-Segmentation)
88
- [实例分割](#Instance-Segmentation)
9+
- [GAN](#GAN)
910
- [人脸检测](#Face-Detection)
1011
- [人体姿态估计](#Human-Pose-Estimation)
12+
- [6DoF 姿态估计](#6DoF-Pose-Estimation)
13+
- [头部姿态估计](#Head-Pose-Estimation)
14+
- [人群密度估计](#Crowd-Counting)
15+
16+
**更新记录：**
17+
18+
- 20190405：添加8篇论文（目标检测、语义分割等方向）
19+
- 20190408：添加6篇论文（目标跟踪、GAN、6DoF姿态估计等方向）
1120

1221
<a name="Object-Detection"></a>
1322

1423
# 目标检测
1524

1625
**Bounding Box Regression with Uncertainty for Accurate Object Detection**
1726

18-
arXiv：<https://arxiv.org/abs/1809.08545>
27+
- arXiv：<https://arxiv.org/abs/1809.08545>
1928

20-
github：<https://github.com/yihui-he/KL-Loss>
29+
- github：<https://github.com/yihui-he/KL-Loss>
2130

2231
<a name="Object-Tracking"></a>
2332

2433
# 目标跟踪
2534

2635
**Fast Online Object Tracking and Segmentation: A Unifying Approach**
2736

28-
arXiv：<https://arxiv.org/abs/1812.05050>
37+
- arXiv：<https://arxiv.org/abs/1812.05050>
38+
39+
- github：<https://github.com/foolwood/SiamMask>
40+
41+
- homepage：<http://www.robots.ox.ac.uk/~qwang/SiamMask>
42+
43+
**Unsupervised Deep Tracking**
44+
45+
- arXiv：<https://arxiv.org/abs/1904.01828>
2946

30-
github：<https://github.com/foolwood/SiamMask>
47+
- github：<https://github.com/594422814/UDT>
3148

32-
homepage：<http://www.robots.ox.ac.uk/~qwang/SiamMask>
49+
- github(PyTorch)：<https://github.com/594422814/UDT_pytorch>
50+
51+
**Target-Aware Deep Tracking**
52+
53+
- arXiv：<https://arxiv.org/abs/1904.01772>
54+
55+
- homepage：<https://xinli-zn.github.io/TADT-project-page/>
3356

3457
<a name="Semantic-Segmentation"></a>
3558

3659
# 语义分割
3760

3861
**Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation**
3962

40-
arXiv：<https://arxiv.org/abs/1903.02120>
63+
- arXiv：<https://arxiv.org/abs/1903.02120>
4164

42-
github：[https://github.com/LinZhuoChen/DUpsampling（非官方）](https://github.com/LinZhuoChen/DUpsampling%EF%BC%88%E9%9D%9E%E5%AE%98%E6%96%B9%EF%BC%89)
65+
- github：[https://github.com/LinZhuoChen/DUpsampling（非官方）](https://github.com/LinZhuoChen/DUpsampling%EF%BC%88%E9%9D%9E%E5%AE%98%E6%96%B9%EF%BC%89)
4366

4467
**Dual Attention Network for Scene Segmentation**
4568

46-
arXiv：<https://arxiv.org/abs/1809.02983>
69+
- arXiv：<https://arxiv.org/abs/1809.02983>
4770

48-
github：<https://github.com/junfu1115/DANet>
71+
- github：<https://github.com/junfu1115/DANet>
4972

5073
**Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images**
5174

52-
arXiv：None
75+
- arXiv：None
5376

54-
github：<https://github.com/chenwydj/ultra_high_resolution_segmentation>
77+
- github：<https://github.com/chenwydj/ultra_high_resolution_segmentation>
5578

5679
<a name="Instance-Segmentation"></a>
5780

5881
# 实例分割
5982

6083
**Mask Scoring R-CNN**
6184

62-
arXiv：<https://arxiv.org/abs/1903.00241>
85+
- arXiv：<https://arxiv.org/abs/1903.00241>
86+
87+
- github：<https://github.com/zjhuang22/maskscoring_rcnn>
88+
89+
<a name="GAN"></a>
90+
91+
# GAN
6392

64-
github：<https://github.com/zjhuang22/maskscoring_rcnn>
93+
**Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis**
94+
95+
- arXiv：<https://arxiv.org/abs/1903.05628>
96+
- github：<https://github.com/HelenMao/MSGAN>
6597

6698
<a name="Face-Detection"></a>
6799

68100
# 人脸检测
69101

70102
**DSFD: Dual Shot Face Detector**
71103

72-
arXiv：<https://arxiv.org/abs/1810.10220>
104+
- arXiv：<https://arxiv.org/abs/1810.10220>
73105

74-
github：<https://github.com/TencentYoutuResearch/FaceDetection-DSFD>
106+
- github：<https://github.com/TencentYoutuResearch/FaceDetection-DSFD>
75107

76108
<a name="Human-Pose-Estimation"></a>
77109

78110
# 人体姿态估计
79111

80112
**Deep High-Resolution Representation Learning for Human Pose Estimation**
81113

82-
arXiv：<https://arxiv.org/abs/1902.09212>
114+
- arXiv：<https://arxiv.org/abs/1902.09212>
115+
116+
- github：<https://github.com/leoxiaobin/deep-high-resolution-net.pytorch>
117+
118+
<a name="6DoF-Pose-Estimation"></a>
119+
120+
# 6DoF姿态估计
121+
122+
**PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation**
123+
124+
- arXiv：<https://arxiv.org/abs/1812.11788>
125+
- github：<https://github.com/zju3dv/pvnet>
126+
127+
<a name="Head-Pose-Estimation"></a>
128+
129+
# 头部姿态估计
130+
131+
**PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation**
132+
133+
- paper：<https://github.com/shamangary/FSA-Net/blob/master/0191.pdf>
134+
- github：<https://github.com/shamangary/FSA-Net>
135+
136+
<a name="Crowd-Counting"></a>
137+
138+
# 人群密度估计
83139

84-
github：<https://github.com/leoxiaobin/deep-high-resolution-net.pytorch>
140+
**Learning from Synthetic Data for Crowd Counting in the Wild**
85141

142+
- arXiv：<https://arxiv.org/abs/1903.03303>
143+
- github：<https://github.com/gjy3035/GCC-SFCN>
144+
- homepage：<https://gjy3035.github.io/GCC-CL/>

0 commit comments

Comments
 (0)