Choose and read a paper, and write a concise summary of this paper. Make it exactly 2 pages - no exceptions! It can be 20 lines short, but not a single line longer... Upload as a PDF only. No Word, RTF, etc. Make absolutely clear in the abstract and text that it is an overview of the published article(s), citing all relevant papers. Add enough relevant citations from the article (probably 3-5) to the most important other articles that are cited there. Add some illustration(s). The essay has a title, author (you), author affiliation (Institute of Computer Science, University of Tartu, …), abstract, introduction, body (with subsections), conclusions and references. Acknowledge your funding. Use a 2-column layout, this is much easier to read. I would strongly recommend LaTeX styles. They are nice, you do not need to worry about layout too much (although you may if you want to procrastinate).
- Rich feature hierarchies for accurate object detection and semantic segmentation
https://arxiv.org/abs/1311.2524
- OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
https://arxiv.org/abs/1312.6229
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
https://arxiv.org/pdf/1406.4729.pdf
- Fast R-CNN
https://arxiv.org/abs/1504.08083
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
https://arxiv.org/abs/1506.01497
- Rapid object detection using a boosted cascade of simple features
https://ieeexplore.ieee.org/document/990517
- Histograms of oriented gradients for human detection
https://ieeexplore.ieee.org/document/1467360
- You Only Look Once: Unified, Real-Time Object Detection
https://arxiv.org/abs/1506.02640
- A convnet for non-maximum suppression
https://arxiv.org/abs/1511.06437
- A discriminatively trained, multiscale, deformable part model
https://ieeexplore.ieee.org/document/4587597
- Focal Loss for Dense Object Detection
https://arxiv.org/abs/1708.02002
- CornerNet: Detecting Objects as Paired Keypoints
https://arxiv.org/abs/1808.01244
- CenterNet: Keypoint Triplets for Object Detection
https://arxiv.org/abs/1904.08189
- Bottom-up Object Detection by Grouping Extreme and Center Points
https://arxiv.org/abs/1901.08043
- End-to-end training of object class detectors for mean average precision
https://arxiv.org/abs/1607.03476
- DeepPose: Human Pose Estimation via Deep Neural Networks
https://ieeexplore.ieee.org/document/6909610
- Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
https://arxiv.org/abs/1406.2984
- DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation
https://arxiv.org/abs/1511.06645
- Stacked Hourglass Networks for Human Pose Estimation
https://arxiv.org/abs/1603.06937
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
https://arxiv.org/abs/1511.00561