Longshortnet: Exploring Temporal and Semantic Features Fusion In Streaming Perception
Authors:
- 4 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
Streaming perception is a fundamental task in autonomous driving that requires a careful balance between the latency and accuracy of the autopilot system. However, current methods for streaming perception are limited as they rely only on the current and adjacent two frames to learn movement patterns, which restricts their ability to model complex scenes, often leading to poor detection results. To address this limitation, we propose LongShortNet, a novel dual-path network that captures long-term temporal motion and integrates it with short-term spatial semantics for real-time perception. Our proposed LongShortNet is notable as it is the first work to extend long-term temporal modeling to streaming perception, enabling spatiotemporal feature fusion. We evaluate LongShortNet on the challenging Argoverse-HD dataset and demonstrate that it outperforms existing state-of-the-art methods with almost no additional computational cost. 1Keywords
All Related Versions
This publication has 32 references indexed in Scilit:
- Decoupling Localization and Classification in Single Shot Temporal Action Detection2019
- Object Detection in Videos by High Quality Object LinkingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
- Video Object Detection with an Aligned Spatial-Temporal Memory2018
- Object Detection in Video with Spatiotemporal Sampling Networks2018
- Fully Motion-Aware Network for Video Object Detection2018
- Towards High Performance Video Object Detection2018
- Path Aggregation Network for Instance Segmentation2018
- Flow-Guided Feature Aggregation for Video Object Detection2017
- Deep Feature Flow for Video Recognition2017
- Fast Semantic Diffusion for Large-Scale Context-Based Image and Video AnnotationIEEE Transactions on Image Processing, 2012