DarkShake-DVS: Event-based Human Action Recognition under Low-light andShaking Camera Conditions

• URL: http://arxiv.org/abs/2605.20680v1
• Date: Wed, 20 May 2026 03:47:47 GMT
• Title: DarkShake-DVS: Event-based Human Action Recognition under Low-light andShaking Camera Conditions
• Abstract summary: Human Action Recognition (HAR) is a fundamental computer vision task with diverse real-world applications.<n>Current research faces two key challenges: absence of a benchmark integrating low-light conditions, 6-DoF motion, and synchronized IMU data.<n>We propose Event-IMU Stabilized HAR (EIS-HAR), with two modules.
• Score: 31.62492338790292
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Human Action Recognition (HAR) is a fundamental computer vision task with diverse real-world applications. Practical deployments often involve low-light environments and unconstrained 6-DoF camera motion, conditions that degrade visual quality, disrupt temporal coherence, and compromise reliability of existing methods. Event cameras, with high low-light sensitivity and microsecond-level temporal resolution, paired with an inertial measurement unit (IMU), present a promising solution. However, current research faces two key challenges: absence of a benchmark integrating low-light conditions, 6-DoF motion, and synchronized IMU data; and lack of effective motion compensation techniques. To address these, we propose Event-IMU Stabilized HAR (EIS-HAR), with two modules. The first is an EIS module that reduces motion blur via a non-linear warping function to reconstruct a motion-compensated input. The second is a HAR module with a four-stage hybrid architecture to efficiently extract spatiotemporal features for accurate action recognition. To alleviate data scarcity, we introduce DarkShake-DVS, the first large-scale event-based HAR benchmark that includes 18,041 realworld clips captured in low light and intense 6-DoF motion, supplemented by synchronized IMU data. Extensive experiments on three datasets demonstrate consistent superiority of EIS-HAR over state-of-the-art methods.

Related papers

• Emo-DVS: A Multimodal Benchmark for Privacy-Aware Emotion Recognition with Event Cameras [28.949201907906765]
  Bio-inspired event cameras capture brightness changes, thereby reducing exposure of facial identity details.<n>We propose the Information-Guided Gated Fusion (IGF) framework, which pre-trains an event encoder on the FAU subset of Emo-DVS to capture fine-grained facial dynamics.<n>To alleviate data scarcity, we introduce Emo-DVS, the first large-scale event-based emotion analysis dataset.
  arXiv  Detail & Related papers  (2026-09-07T01:55:44Z)
• MotionGS-SLAM: Event-Modulated Gaussian Splatting for Motion-Blur Robust SLAM [10.233658861023612]
  Current Vision-based SLAM systems fail catastrophically when motion blur corrupts the visual input.<n>We present MotionGS-SLAM, which reimagines motion blur handling through a paradigm shift.<n>We show significant improvements over state-of-the-art methods in trajectory accuracy and map quality under severe high-motion conditions.
  arXiv  Detail & Related papers  (2026-08-15T04:20:51Z)
• A Height-Constrained 2-Point Minimal Solver for Pose Estimation from Active LED Markers with Event Cameras [51.7262911415172]
  We develop an event-based active marker system to collect real-world data with ground truth from a motion capture system.<n>Experiments on both synthetic and real data demonstrate improved accuracy over the state-of-the-art P2P solver.
  arXiv  Detail & Related papers  (2026-08-10T12:19:24Z)
• Event-based SLAM Benchmark for High-Speed Maneuvers [68.148886127117]
  Event-based cameras are bio-inspired sensors with pixels that independently and asynchronously respond to brightness changes at microsecond resolution.<n>Existing event-based approaches, although successful in mitigating motion blur caused by high-speed maneuvers, suffer from many limitations.<n>We introduce a benchmarking framework for event-based state estimation, called EvSLAM, characterized by sufficient variation in data collection platforms.
  arXiv  Detail & Related papers  (2026-04-27T04:36:41Z)
• FlashCap: Millisecond-Accurate Human Motion Capture via Flashing LEDs and Event-Based Vision [70.26305628326237]
  A millisecond difference may determine victory or defeat in sports competitions.<n>PMT is achieved using high-speed RGB cameras in specialized scenarios such as the Olympic Games.<n>We develop FlashCap, the first flashing LED-based MoCap system for PMT.
  arXiv  Detail & Related papers  (2026-03-20T08:59:37Z)
• Edged USLAM: Edge-Aware Event-Based SLAM with Learning-Based Depth Priors [1.504944269180605]
  Event cameras mitigate these issues with high temporal resolution and high dynamic range.<n>We present Edged USLAM, a hybrid visual-inertial system that extends Ultimate SLAM with an edge-aware front-end and a lightweight depth module.
  arXiv  Detail & Related papers  (2026-03-09T09:28:52Z)
• HAD: Hierarchical Asymmetric Distillation to Bridge Spatio-Temporal Gaps in Event-Based Object Tracking [80.07224739976911]
  Event cameras offer exceptional temporal resolution and a range (modal)<n> RGB cameras excel at capturing rich texture with high resolution, whereas event cameras offer exceptional temporal resolution and a range (modal)
  arXiv  Detail & Related papers  (2025-10-22T13:15:13Z)
• EDmamba: Rethinking Efficient Event Denoising with Spatiotemporal Decoupled SSMs [23.63023704154084]
  Event cameras provide micro-second latency and broad dynamic range, yet their raw streams are marred by spatial artifacts.<n>We introduce EDmamba, a compact event-denoising framework that embraces the key insight that spatial and temporal noise arise from different physical mechanisms.<n>This decoupled design distills the network to only 88.9K parameters and 2.27GPs, enabling realtime throughput of 100K events in 68ms on a single Transformer.
  arXiv  Detail & Related papers  (2025-05-08T16:27:27Z)
• FUSE: Label-Free Image-Event Joint Monocular Depth Estimation via Frequency-Decoupled Alignment and Degradation-Robust Fusion [92.4205087439928]
  Image-event joint depth estimation methods leverage complementary modalities for robust perception, yet face challenges in generalizability.<n>We propose the Self-supervised Transfer (PST) and the FrequencyDe-coupled Fusion module (FreDF)<n>PST establishes cross-modal knowledge transfer through latent space alignment with image foundation models, effectively mitigating data scarcity.<n>FreDF explicitly decouples high-frequency edge features from low-frequency structural components, resolving modality-specific frequency mismatches.<n>This combined approach enables FUSE to construct a universal image-event that only requires lightweight decoder adaptation for target datasets.
  arXiv  Detail & Related papers  (2025-03-25T15:04:53Z)
• Motion-prior Contrast Maximization for Dense Continuous-Time Motion Estimation [34.529280562470746]
  We introduce a novel self-supervised loss combining the Contrast Maximization framework with a non-linear motion prior in the form of pixel-level trajectories. Their effectiveness is demonstrated in two scenarios: In dense continuous-time motion estimation, our method improves the zero-shot performance of a synthetically trained model by 29%.
  arXiv  Detail & Related papers  (2024-07-15T15:18:28Z)
• LIF-Seg: LiDAR and Camera Image Fusion for 3D LiDAR Semantic Segmentation [78.74202673902303]
  We propose a coarse-tofine LiDAR and camera fusion-based network (termed as LIF-Seg) for LiDAR segmentation. The proposed method fully utilizes the contextual information of images and introduces a simple but effective early-fusion strategy. The cooperation of these two components leads to the success of the effective camera-LiDAR fusion.
  arXiv  Detail & Related papers  (2021-08-17T08:53:11Z)

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.