# Seeing Through Fog: Towards Fog-Invariant Action Recognition

Source: [Seeing Through Fog: Towards Fog-Invariant Action Recognition](<https://www.sota2.com/research/paper/6a0e91a2f984739ed6738bff>)

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

Data updated: 2026-05-22T05:00:05.162Z

Authors: Enqi Liu, Liyuan Pan, Zhi Gao, Lingzhi Li, Qing Li

Published: 2026-05-20T03:09:18.000Z

## Abstract

Foggy conditions are commonly encountered in real-world applications; however, existing action recognition approaches typically assume favorable weather and high-quality video inputs. On foggy days, unpredictable visibility degradation and reduced contrast obstruct the extraction of semantic cues, posing significant challenges for current action recognition methods. In this paper, we mitigate the issues faced in action recognition under foggy conditions by employing two strategies. First, we present FogAct, the first benchmark dataset for foggy action recognition, consisting of paired clean and foggy videos captured with a stereo camera system. The dataset spans 10 scenes and 55 action categories, comprising nearly 10,000 video clips. Second, we propose FogNet, a two-stream CLIP model that discovers fog-invariant semantic information hidden behind the degraded videos. FogNet learns robust representations of foggy videos with guidance from clean videos, effectively capturing shared structural and motion cues between clean and foggy videos. Extensive experiments on FogAct and three other popular datasets demonstrate that our method achieves competitive performance compared with state-of-the-art (SOTA) approaches. Our FogAct and FogNet are given in our project page.

## 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.

- [Action Recognition on FogAct 1.0 (test)](<https://www.sota2.com/research/sota/action-recognition-on-fogact-1-0-test.md>): Action Recognition; FogAct 1.0 (test); Top-1 Accuracy: 88.7.

- [Action Recognition on Foggy UCF-101, HMDB-51, and Kinetics-100](<https://www.sota2.com/research/sota/action-recognition-on-foggy-ucf-101-hmdb-51-and-kinetics-100.md>): Action Recognition; UCF-101, HMDB-51, and Kinetics-100 synthesized foggy versions; Accuracy (UCF-101 Foggy): 93.2.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.20645>)

[PDF](<https://arxiv.org/pdf/2605.20645.pdf>)