# Workshop on Autonomous Driving at CVPR 2021: Technical Report for Streaming Perception Challenge

Source: [Workshop on Autonomous Driving at CVPR 2021: Technical Report for Streaming Perception Challenge](<https://www.sota2.com/research/paper/68fa6a7b1e209131cea28761>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:49.074Z

Authors: Songyang Zhang, Lin Song, Songtao Liu, Zheng Ge, Zeming Li, Xuming He, Jian Sun

Published: 2021-07-27T06:36:06.000Z

## Abstract

In this report, we introduce our real-time 2D object detection system for the realistic autonomous driving scenario. Our detector is built on a newly designed YOLO model, called YOLOX. On the Argoverse-HD dataset, our system achieves 41.0 streaming AP, which surpassed second place by 7.8/6.1 on detection-only track/fully track, respectively. Moreover, equipped with TensorRT, our model achieves the 30FPS inference speed with a high-resolution input size (e.g., 1440-2304). Code and models will be available at https://github.com/Megvii-BaseDetection/YOLOX

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Streaming Perception on Argoverse-HD v1.0 (test)](<https://www.sota2.com/research/sota/streaming-perception-on-argoverse-hd-v1-0-test.md>): Streaming Perception; Argoverse-HD v1.0 (test); sAP: 40.2.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2108.04230>)

[PDF](<https://arxiv.org/pdf/2108.04230.pdf>)
