YOLO-MAXVOD for Real-Time Video Object Detection
Lists
Only you see this
Abstract
Video Object Detection (VOD) is one of the fundamental problems in video understanding with applications ranging from surveillance to autonomous driving. But many such real-world applications are unable to leverage the existing VOD models owing to their higher computational complexity which reduces inference speed. Single-stage still-image object detection models are naively used without any use of video information. In this paper, we present YOLOX based VOD model, YOLO-MaxVOD, which provides a better trade-off between accuracy and inference time than the current real-time VOD solutions. Specifically, we propose a temporal fusion module that integrates within the YOLOX architecture to take advantage of the high speed that the YOLOX model offers. In our experimentation on the Imagenet-VID dataset, we show that YOLO-MaxVOD shows 4.4-5.6% AP50 improvement over the baseline YOLOX, across different versions, with just a 1-2 ms increase in latency on NVIDIA 1080Ti GPU.
BibTeX
@inproceedings{moturi2023yolo,
author = {Pradeep Moturi and Mukund Khanna and Kunal Singh},
title = {{YOLO-MAXVOD for Real-Time Video Object Detection}},
booktitle = {ICIP},
year = {2023},
url = {https://openreview.net/forum?id=7EWbuyzWIV},
}Loading related content...