Hassan Mahichi

YOLO, a new approach to object detection, prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background. Finally, YOLO learns very general representations of objects. It outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork. Object tracking is the cornerstone of many visual analytics systems. This paper presents a hybrid tracker that leverages motion information from the compressed video stream and a general-purpose semantic object detector acting on decoded frames to construct a fast and efficient tracking engine. Action recognition and human pose estimation are closely related but both problems are generally handled as distinct tasks in the literature. In this work, we propose a multitask framework for jointly ۲D and ۳D pose estimation from still images and human action recognition fromvideo sequences.

Deep Learning, Objects Detection, Object Tracking,۳D Pose Estimate, , Yolo