Seeing Through Fog: Towards Fog-Invariant Action Recognition

• URL: http://arxiv.org/abs/2605.20645v1
• Date: Wed, 20 May 2026 03:09:18 GMT
• Title: Seeing Through Fog: Towards Fog-Invariant Action Recognition
• Abstract summary: We present FogAct, the first benchmark dataset for foggy action recognition.<n>We propose FogNet, a two-stream CLIP model that discovers fog-invariant semantic information hidden behind degraded videos.<n>Our method achieves competitive performance compared with state-of-the-art (SOTA) approaches.
• Score: 31.5381777659518
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Learning Unified Video and Image Representation for Video Face Forgery Detection [49.19035628283472]
  Existing methods for video face forgery detection assume that all frames in a forged video are manipulated.<n>We propose a novel framework, UVIF, that utilizes additional annotated images to provide fine-grained supervision for detecting partial forgeries in videos.<n>UVIF employs a unified encoder and a multi-task learning paradigm to jointly model facial videos and images for boosted video face forgery detection.
  arXiv  Detail & Related papers  (2026-08-13T10:25:59Z)
• FogGuard: guarding YOLO against fog using perceptual loss [5.868532677577194]
  FogGuard is a fog-aware object detection network designed to address the challenges posed by foggy weather conditions. FogGuard compensates for foggy conditions in the scene by incorporating YOLOv3 as the baseline algorithm. Our network significantly improves performance, achieving a 69.43% mAP compared to YOLOv3's 57.78% on the RTTS dataset.
  arXiv  Detail & Related papers  (2024-03-13T20:13:25Z)
• Genuine Knowledge from Practice: Diffusion Test-Time Adaptation for Video Adverse Weather Removal [53.15046196592023]
  We introduce test-time adaptation into adverse weather removal in videos. We propose the first framework that integrates test-time adaptation into the iterative diffusion reverse process.
  arXiv  Detail & Related papers  (2024-03-12T14:21:30Z)
• Neuromorphic Synergy for Video Binarization [54.195375576583864]
  Bimodal objects serve as a visual form to embed information that can be easily recognized by vision systems. Neuromorphic cameras offer new capabilities for alleviating motion blur, but it is non-trivial to first de-blur and then binarize the images in a real-time manner. We propose an event-based binary reconstruction method that leverages the prior knowledge of the bimodal target's properties to perform inference independently in both event space and image space. We also develop an efficient integration method to propagate this binary image to high frame rate binary video.
  arXiv  Detail & Related papers  (2024-02-20T01:43:51Z)
• ScatterNeRF: Seeing Through Fog with Physically-Based Inverse Neural Rendering [83.75284107397003]
  We introduce ScatterNeRF, a neural rendering method which renders scenes and decomposes the fog-free background. We propose a disentangled representation for the scattering volume and the scene objects, and learn the scene reconstruction with physics-inspired losses. We validate our method by capturing multi-view In-the-Wild data and controlled captures in a large-scale fog chamber.
  arXiv  Detail & Related papers  (2023-05-03T13:24:06Z)
• Weakly-Supervised Action Detection Guided by Audio Narration [50.4318060593995]
  We propose a model to learn from the narration supervision and utilize multimodal features, including RGB, motion flow, and ambient sound. Our experiments show that noisy audio narration suffices to learn a good action detection model, thus reducing annotation expenses.
  arXiv  Detail & Related papers  (2022-05-12T06:33:24Z)
• FIFO: Learning Fog-invariant Features for Foggy Scene Segmentation [14.932318540666548]
  We propose a new method for learning semantic segmentation models robust against fog. Its key idea is to consider the fog condition of an image as its style and close the gap between images with different fog conditions. Our method substantially outperforms previous work on three real foggy image datasets.
  arXiv  Detail & Related papers  (2022-04-04T15:33:42Z)
• ASCNet: Self-supervised Video Representation Learning with Appearance-Speed Consistency [62.38914747727636]
  We study self-supervised video representation learning, which is a challenging task due to 1) a lack of labels for explicit supervision and 2) unstructured and noisy visual information. Existing methods mainly use contrastive loss with video clips as the instances and learn visual representation by discriminating instances from each other. In this paper, we observe that the consistency between positive samples is the key to learn robust video representations.
  arXiv  Detail & Related papers  (2021-06-04T08:44:50Z)
• Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition [86.31412529187243]
  Few-shot video recognition aims at learning new actions with only very few labeled samples. We propose a depth guided Adaptive Meta-Fusion Network for few-shot video recognition which is termed as AMeFu-Net.
  arXiv  Detail & Related papers  (2020-10-20T03:06:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.