GBU-Palm: A Multimodal Video Dataset and Benchmark for Palm Presentation Attack Detection

• URL: http://arxiv.org/abs/2608.14389v1
• Date: Fri, 14 Aug 2026 15:31:48 GMT
• Title: GBU-Palm: A Multimodal Video Dataset and Benchmark for Palm Presentation Attack Detection
• Abstract summary: GBU-Palm is a large-scale multimodal video dataset and benchmark containing 21,326 videos from 105 subjects and 210 palms.<n>We construct leakage-controlled protocols that separate palm identity and attack lineage and benchmark four representative video architectures.<n>Results reveal substantial architecture-dependent degradation under environmental shift and show that RGB-NIR fusion does not consistently outperform RGB-only input.
• Score: 73.00315875431374
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing palm presentation attack detection (PAD) datasets are often limited by static imagery, restricted acquisition conditions, or insufficient multimodal video data, hindering systematic evaluation across environments, modalities, and attack types. We present GBU-Palm, a large-scale multimodal video dataset and benchmark containing 21,326 videos from 105 subjects and 210 palms across six acquisition environments, including bona fide, Print, and Replay presentations, with 6,310 synchronized RGB-NIR samples. We construct leakage-controlled protocols that separate palm identity and attack lineage and benchmark four representative video architectures under environment-matched and held-out-environment settings. Results reveal substantial architecture-dependent degradation under environmental shift and show that RGB-NIR fusion does not consistently outperform RGB-only input. We further analyze model behavior through true accept (TA), true reject (TR), false accept (FA), and false reject (FR) decomposition, spectral masking, temporal-order intervention, and frozen-backbone NIR probing, revealing distinct failure patterns and evidence utilization across architectures. GBU-Palm provides a unified and challenging benchmark for developing and evaluating robust multimodal palm PAD methods under cross-environment conditions.

Related papers

• LaP-Forensics: Latent-Pixel Consistency Guided Multimodal Reasoning for Deepfake Detection [11.780720481629837]
  We present LaP-Forensics, a framework that augments RGB semantics with reconstruction-based forensic evidence.<n> Independent projectors encode the RGB image and residual map before a structured Where-What-Why model predicts a textual analysis and an artifact mask.<n>Experiments show cross-generator detection on UniversalFakeDetect and competitive artifact localization on the official SynthScars benchmark.
  arXiv  Detail & Related papers  (2026-07-28T16:45:52Z)
• Active Adversarial Perturbation-driven Associative Memory Retrieval for RGB-Event Visual Object Tracking [58.338848435042536]
  RGB-Event tracking improves localization by fusing RGB appearance textures and dense temporal motion cues from event sensors.<n>Real-world scenes suffer diverse structured signal degradations that hinder traditional multi-modal fusion.<n>We present a hierarchical perturbation and retrieval framework tailored for RGB-Event tracking with robustness against partial target missing and modal degradation.
  arXiv  Detail & Related papers  (2026-06-24T23:34:06Z)
• X-Palm: Paired Multispectral-to-Smartphone Dataset for Cross-Domain Palmprint Authentication [29.884043808473006]
  X-Palm is a cross-domain dataset comprising 6,006 palm images from 103 individuals (206 hands)<n>X-Palm is the first palmprint dataset providing novel paired-identity acquisition.<n>Our benchmarks of 12 SOTA models reveal that while existing methods achieve high performance on controlled data, they experience severe performance collapse on X-Palm.
  arXiv  Detail & Related papers  (2026-06-07T03:27:36Z)
• MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation [88.7702943548674]
  We introduce MSAVBench, the first comprehensive benchmark and adaptive hybrid evaluation framework for multi-shot audio-video generation.<n>Our benchmark spans four key dimensions, video, audio, shot, and reference, covering diverse task settings, varying shot counts of up to 15, and challenging non-realistic scenarios.<n> MSAVBench achieves high alignment with human judgments, reaching a Spearman rank correlation of 91.5%.
  arXiv  Detail & Related papers  (2026-05-19T17:59:33Z)
• Robust Promptable Video Object Segmentation [67.1533741758339]
  This paper offers the first comprehensive study on robust PVOS (RobustPVOS)<n>We first construct a new, comprehensive benchmark with two real-world evaluation datasets of 351 video clips and more than 2,500 object masks.<n>We present a new RobustPVOS method, dubbed Memory-object-conditioned Gated-rank Adaptation (MoGA)
  arXiv  Detail & Related papers  (2026-05-12T11:55:31Z)
• iPhoneBlur: A Difficulty-Stratified Benchmark for Consumer Device Motion Deblurring [0.0]
  This work introduces iPhoneBlur, a difficulty-stratified benchmark of 7,400 image pairs synthesized from high-framerate iPhone 17 Pro videos.<n>Each sample includes comprehensive metadata enabling investigation of ISP-aware and difficulty-adaptive restoration strategies.
  arXiv  Detail & Related papers  (2026-05-07T10:41:16Z)
• Gaze4HRI: Zero-shot Benchmarking Gaze Estimation Neural-Networks for Human-Robot Interaction [8.819673391477036]
  We introduce Gaze4HRI, a large-scale dataset designed to evaluate state-of-the-art performance against critical HRI variables.<n>Our benchmark reveals that all evaluated methods fail in at least one condition, identifying steeply-downward gaze as a universal failure point.
  arXiv  Detail & Related papers  (2026-05-06T11:17:18Z)
• A New Dataset and Framework for Robust Road Surface Classification via Camera-IMU Fusion [3.571515153090507]
  Road surface classification (RSC) is a key enabler for environment-aware predictive maintenance systems.<n>Existing RSC techniques often fail to generalize beyond narrow operational conditions.<n>This work introduces a multimodal framework that fuses images and inertial measurements.
  arXiv  Detail & Related papers  (2026-01-28T18:46:29Z)
• EMPalm: Exfiltrating Palm Biometric Data via Electromagnetic Side-Channels [54.460942487872416]
  EM emissions leak palm biometric information.<n> EMPalm is an attack framework that covertly recovers both palmprint and palmvein images from eavesdropped EM signals.
  arXiv  Detail & Related papers  (2025-10-08T20:50:19Z)
• Multi-modal Multi-platform Person Re-Identification: Benchmark and Method [58.59888754340054]
  MP-ReID is a novel dataset designed specifically for multi-modality and multi-platform ReID.<n>This benchmark compiles data from 1,930 identities across diverse modalities, including RGB, infrared, and thermal imaging.<n>We introduce Uni-Prompt ReID, a framework with specific-designed prompts, tailored for cross-modality and cross-platform scenarios.
  arXiv  Detail & Related papers  (2025-03-21T12:27:49Z)

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.