MambaGaze: Bidirectional Mamba with Explicit Missing Data Modeling for Cognitive Load Assessment from Eye-Gaze Tracking Data

• URL: http://arxiv.org/abs/2605.22775v1
• Date: Thu, 21 May 2026 17:33:41 GMT
• Title: MambaGaze: Bidirectional Mamba with Explicit Missing Data Modeling for Cognitive Load Assessment from Eye-Gaze Tracking Data
• Abstract summary: Real-time cognitive load assessment from eye-tracking signals could potentially enable adaptive human-centered AI.<n>We propose MambaGaze, a framework to handle frequent data missingness from blinks and tracking failures.<n>We show that MambaGaze achieves 76.8% and 73.1% accuracy, respectively, outperforming CNN, Transformer, ResNet, and VGG baselines by 4-12 percentage points.
• Score: 5.256332889764464
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Real-time cognitive load assessment from eye-tracking signals could potentially enable adaptive human-centered-AI such as safety-critical applications such as driver vigilance monitoring or automated flight deck assistance, yet two challenges persist: handling frequent data missingness from blinks and tracking failures, and efficiently modeling long-range temporal dependencies. We propose MambaGaze, a framework that addresses these challenges through 1) XMD encoding, which augments raw features with observation masks and time-deltas to explicitly model data uncertainty, and 2) bidirectional Mamba-2, which captures temporal dependencies with linear computational complexity. Experiments on CLARE and CL-Drive datasets under leave-one-subject-out evaluation show that MambaGaze achieves 76.8% and 73.1% accuracy, respectively, outperforming CNN, Transformer, ResNet, and VGG baselines by 4-12 percentage points. Edge deployment benchmarks on NVIDIA Jetson platforms demonstrate real-time inference at 43-68 FPS with power consumption below 7.5W, confirming feasibility for wearable cognitive load monitoring.

Related papers

• SpikingMOT: A Spike-Driven Multi-Object Tracker [75.7974381720717]
  SpikingMOT is proposed as a spike-driven tracker that adaptively models sparse trajectory dynamics with spiking neural networks (SNNs)<n>With this brain-inspired loop, SpikingMOT achieves state-of-the-art performance in extensive experiments.
  arXiv  Detail & Related papers  (2026-07-22T08:03:23Z)
• EvoEye: Self-Evolving Runtime Monitoring for Autonomous Driving Systems [15.753537830005596]
  We propose EvoEye, which identifies the current monitor's errors, generates informative executions accordingly, and updates the monitor through self-evolution.<n>To enable effective self-evolution, EvoEye combines a capable runtime monitor with targeted scenario acquisition.<n> FusionMonitor improves frame-level Recall by up to 37.8 percentage points at a false positive rate of 0.05, with 2.49 ms latency and 2.8-4.2 seconds of median warning time.<n>BlindSpotEvolver outperforms uniform and violation-oriented sampling by up to 13.2 F1 points on previously missed unsafe contexts.
  arXiv  Detail & Related papers  (2026-07-04T08:03:31Z)
• PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents [53.369140518949656]
  We introduce PersonalAI 2.0 (PAI-2), a novel framework to enhance large language model (LLM) based systems through integration of external knowledge graphs (KG)<n>The proposed approach addresses key limitations of existing Retrieval-Augmented Generation (GraphRAG) methods by incorporating a dynamic, multistage query processing pipeline.<n>We show that use of graph algorithms (e.g. BeamSearch, WaterCircles) gain superior results compared to standard flatten retriever on average 6%, while enabled search plan enhancement mechanism gain 18% boost compared to disabled one by LLM-as-a-Judge across six datasets.
  arXiv  Detail & Related papers  (2026-05-13T13:06:30Z)
• TinyGLASS: Real-Time Self-Supervised In-Sensor Anomaly Detection [7.978059159334374]
  Anomaly detection plays a key role in industrial quality control, where defects must be identified despite the scarcity of labeled faulty samples.<n>Recent self-supervised approaches, such as GLASS, learn normal visual patterns using only defect-free data and have shown strong performance on industrial benchmarks.<n>This work introduces TinyGLASS, a lightweight adaptation of the GLASS framework designed for real-time edge and in-sensor anomaly detection.
  arXiv  Detail & Related papers  (2026-03-17T12:31:34Z)
• Modeling Information Blackouts in Missing Not-At-Random Time Series Data [0.0]
  Large-scale traffic forecasting relies on fixed sensor networks that often exhibit blackouts.<n>We propose a latent state-space framework that jointly models traffic dynamics via a linear dynamical system.<n>Explicit MNAR modeling provides a consistent but smaller additional improvement on real data.
  arXiv  Detail & Related papers  (2026-01-04T11:03:13Z)
• Learning to Track Any Points from Human Motion [55.831218129679144]
  We propose an automated pipeline to generate pseudo-labeled training data for point tracking.<n>A point tracking model trained on AnthroTAP achieves annotated state-of-the-art performance on the TAP-Vid benchmark.
  arXiv  Detail & Related papers  (2025-07-08T17:59:58Z)
• What You Have is What You Track: Adaptive and Robust Multimodal Tracking [72.92244578461869]
  We present the first comprehensive study on tracker performance with temporally incomplete multimodal data.<n>Our model achieves SOTA performance across 9 benchmarks, excelling in both conventional complete and missing modality settings.
  arXiv  Detail & Related papers  (2025-07-08T11:40:21Z)
• TrackingMiM: Efficient Mamba-in-Mamba Serialization for Real-time UAV Object Tracking [4.6672950054734255]
  We propose TrackingMiM, a minimal-computation burden model for handling image sequence of tracking problem.<n>In our framework, the mamba scan is performed in a nested way while independently process temporal and spatial coherent patch tokens.
  arXiv  Detail & Related papers  (2025-07-02T09:40:37Z)
• LSM-2: Learning from Incomplete Wearable Sensor Data [65.58595667477505]
  This paper introduces the second generation of Large Sensor Model (LSM-2) with Adaptive and Inherited Masking (AIM)<n>AIM learns robust representations directly from incomplete data without requiring explicit imputation.<n>Our LSM-2 with AIM achieves the best performance across a diverse range of tasks, including classification, regression and generative modeling.
  arXiv  Detail & Related papers  (2025-06-05T17:57:11Z)
• Tracking Meets Large Multimodal Models for Driving Scenario Understanding [76.71815464110153]
  Large Multimodal Models (LMMs) have recently gained prominence in autonomous driving research.<n>We propose to integrate tracking information as an additional input to recover 3D spatial and temporal details.<n>We introduce a novel approach for embedding this tracking information into LMMs to enhance their understanding of driving scenarios.
  arXiv  Detail & Related papers  (2025-03-18T17:59:12Z)
• 8-Calves Image dataset [0.8233028449337972]
  We introduce the 8-Calves dataset, a challenging benchmark for multi-animal detection, tracking, and identification.<n>It features a one-hour video of eight Holstein Friesian calves in a barn, with frequent occlusions, motion blur, and diverse poses.<n>A semi-grained pipeline using a fine-tuned YOLOv8 detector and ByteTrack, followed by manual correction, provides over 537,000 bounding boxes with temporal identity labels.
  arXiv  Detail & Related papers  (2025-03-17T23:47:52Z)
• MambaNUT: Nighttime UAV Tracking via Mamba-based Adaptive Curriculum Learning [5.9089796108568855]
  We propose a pure Mamba-based tracking framework (MambaNUT) that employs a state space model with linear complexity as its backbone.<n>We introduce an adaptive curriculum learning (ACL) approach that adjusts dynamically sampling strategies and loss weights.<n>Exhaustive experiments on multiple nighttime UAV tracking benchmarks demonstrate that the proposed MambaNUT achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-12-01T00:51:23Z)
• SIGMA: Selective Gated Mamba for Sequential Recommendation [56.85338055215429]
  Mamba, a recent advancement, has exhibited exceptional performance in time series prediction.<n>We introduce a new framework named Selective Gated Mamba ( SIGMA) for Sequential Recommendation.<n>Our results indicate that SIGMA outperforms current models on five real-world datasets.
  arXiv  Detail & Related papers  (2024-08-21T09:12:59Z)

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.