# S3-Net: A Fast and Lightweight Video Scene Understanding Network by Single-shot Segmentation

Source: [S3-Net: A Fast and Lightweight Video Scene Understanding Network by Single-shot Segmentation](<https://www.sota2.com/research/paper/68fa68a61e209131cea1d664>)

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

Data updated: 2025-10-25T22:41:59.280Z

Authors: Yuan Cheng, Yuchao Yang, Hai-Bao Chen, Ngai Wong, Hao Yu

Published: 2020-11-04T13:09:26.000Z

## Abstract

Real-time understanding in video is crucial in various AI applications such as autonomous driving. This work presents a fast single-shot segmentation strategy for video scene understanding. The proposed net, called S3-Net, quickly locates and segments target sub-scenes, meanwhile extracts structured time-series semantic features as inputs to an LSTM-based spatio-temporal model. Utilizing tensorization and quantization techniques, S3-Net is intended to be lightweight for edge computing. Experiments using CityScapes, UCF11, HMDB51 and MOMENTS datasets demonstrate that the proposed S3-Net achieves an accuracy improvement of 8.1% versus the 3D-CNN based approach on UCF11, a storage reduction of 6.9x and an inference speed of 22.8 FPS on CityScapes with a GTX1080Ti GPU.

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2011.02265>)

[PDF](<https://arxiv.org/pdf/2011.02265.pdf>)
