SS2023 Project - Object Detection in Videos
Improving Detection in Videos
Supervisor: Khurram Azeem Hashmi
Tasks
- Re-implementing current SOTA Video object detection methods.
- Design and incorporate novel modules in the pipeline to improve results.
- Benchmarking performance on at-least 2 datasets.
Expected Skills
- PyTorch, GitHub, Deep Learning
- Proficient theoretical knowledge of Object Detection Algorithms and CNNs.
Related Literature
[1] Gong, Tao, et al. “Temporal ROI align for video object recognition.” Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 35. No. 2. 2021.
[2] Zhou, Qianyu, et al. “TransVOD: End-to-end Video Object Detection with Spatial-Temporal Transformers.” arXiv preprint arXiv:2201.05047 (2022).
Subscribe
Subscribe to this blog via RSS.
Recent Posts
- SS2023 Project - Deep Learning Model Compression Techniques for High Speed Object Detection Saif Khan (03 Apr 2023)
- SS2023 Project - Optimize a Human Pose Estimation Network using Knowledge Distillation Saif Khan (03 Apr 2023)
- SS2023 Project - Object Detection in Videos Saif Khan (03 Apr 2023)
- Successful Ovation Summer Academy 2017 Marcus Liwicki (22 Sep 2017)
Popular Tags
intro fun official lecture very deep learning publications ijcnn arxiv events mindstorm object detection pose estimation