SMSnet: Semantic motion segmentation using deep convolutional neural networks

By Johan Vertens, Abhinav Valada, Wolfram Burgard. 2017

68 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Ciarán Hughes
2. Patrick Pérez
3. Yassine Ruichek
4. Karl Amende
5. Stefan Milz
6. Christian Witt
7. Martin Simon
8. Senthil Kumar Yogamani

In Computer Vision and Pattern Recognition

1. Yassine Ruichek
2. Fahad Lateef
3. Senthil Kumar Yogamani
4. Ganesh Sistu
5. Stefan Milz
6. Sumanth Chennupati
7. Karl Amende
8. Samir A. Rawashdeh

Citations in the corpus

• WoodScape: A Multi-Task, Multi-Camera Fisheye Dataset for Autonomous Driving (2019, background): “This has been explored in [49, 57, 48] for narrow angle cameras.”
• NeurAll: Towards a Unified Visual Perception Model for Automated Driving (2019, background): “2) Multi-stream learning: Prior works [39], [40] show that motion and depth cues can be obtained from two-stream architectures.”
• Survey on semantic segmentation using deep learning techniques (2019, background): “Upsampling / Deconvolution Semantic Motion Segmentation Network (SMSNet)[84] Motion feature component: FlowNet2 architecture[85] Semantic Segmentation component: AdapNet architecture”
• NeurAll: Towards a Unified Model for Visual Perception in Automated Driving (2019, background): “2) Multi-stream learning: Prior works [38], [39] show that motion and depth cues can be obtained from two-stream architectures.”