Even-Order Taylor Approximation-Based Feature Refinement and Dynamic Aggregation Model for Video Object Detection
Open Access
- 18 October 2023
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 12 (20) , 4305
Abstract
Video object detection (VOD) is a sophisticated visual task. It is a consensus that is used to find effective supportive information from correlation frames to boost the performance of the model in VOD tasks. In this paper, we not only improve the method of finding supportive information from correlation frames but also strengthen the quality of the features extracted from the correlation frames to further strengthen the fusion of correlation frames so that the model can achieve better performance. The feature refinement module FRM in our model refines the features through the key–value encoding dictionary based on the even-order Taylor series, and the refined features are used to guide the fusion of features at different stages. In the stage of correlation frame fusion, the generative MLP is applied in the feature aggregation module DFAM to fuse the refined features extracted from the correlation frames. Experiments adequately demonstrate the effectiveness of our proposed approach. Our YOLOX-based model can achieve 83.3% AP50 on the ImageNet VID dataset.Keywords
Funding Information
- National Key R&D Program of China (2020YFB2104402)
This publication has 37 references indexed in Scilit:
- YOLO9000: Better, Faster, Stronger2017
- Deep Feature Flow for Video Recognition2017
- SSD: Single Shot MultiBox Detector2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Fast R-CNN2015
- Fully convolutional networks for semantic segmentation2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Microsoft COCO: Common Objects in Context2014
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998