
2021.11.30 Review https://pdfs.semanticscholar.org/87db/49a14a1dd0e3d672e1144dc13354d892558d.pdf https://www.semanticscholar.org/paper/A-Review-of-Video-Object-Detection%3A-Datasets%2C-and-Zhu-Wei/3c03cb37863eea4be5e01f407d6899620dc4d254?p2df www.semanticscholar.org --- Shortcomings of frame by frame basis object detection in video lack of computational efficiency due to redundancy across image ..

https://arxiv.org/pdf/2011.14204.pdf --- Proposed by Amazon Alexa Natural Understanding Team Limitations of conventional class-aware detection Hinders the adoption of trained detectors in real-world applications due to the added cost of retraining them for application specific object types such detectors cannot be used in applications like obstacle detection, where it is more important to determ..

2022.02.08 Review --- https://arxiv.org/pdf/2104.02243v2.pdf Background Semantic Segmenation classifying each pixel in an image from a predefined set of classes Knowledge Distillation Process of transferring knowledge from model to other model that has different structure usaually, model compression method in which a small model is trained to mimic a pre-trained, larger model start to research f..

2022.04.05 Review --- https://github.com/MCG-NJU/AdaMixer GitHub - MCG-NJU/AdaMixer: [CVPR 2022 Oral] AdaMixer: A Fast-Converging Query-Based Object Detector [CVPR 2022 Oral] AdaMixer: A Fast-Converging Query-Based Object Detector - GitHub - MCG-NJU/AdaMixer: [CVPR 2022 Oral] AdaMixer: A Fast-Converging Query-Based Object Detector github.com https://arxiv.org/pdf/2203.16507.pdf --- Goal To simpl..

2022.10.13에 직접 리뷰 했던 것을 좀 지나서 블로그에 올립니다. 최신 정보는 아닌 점 참고 바랍니다. YOLO (You Only Look Once) Single stage real-time object detector Performance, Accruate, Active community featurized through a backbone, combined and mixed in the neck, passed along to the head YOLO-v7 AlexeyAB, WongKinYiu AlexeyAB took up the YOLO torch from the original author. Joseph Redmon, when Redmon quit the CV industry due to e..