Bridging the Visual-to-Physical Gap: Physically Aligned Representations for Fall Risk Analysis

• URL: http://arxiv.org/abs/2603.13410v1
• Date: Thu, 12 Mar 2026 11:29:54 GMT
• Title: Bridging the Visual-to-Physical Gap: Physically Aligned Representations for Fall Risk Analysis
• Abstract summary: PHARL learns physically meaningful fall representations without requiring clinicaloutcome labels.<n>Experiments show that PHARL consistently improves risk-aligned representation quality overvisual-only baselines.
• Score: 3.1812226135012467
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-based fall analysis has advanced rapidly, but a key bottleneck remains: visually similarmotions can correspond to very different physical outcomes because small differences in contactmechanics and protective responses are hard to infer from appearance alone. Most existingapproaches handle this by supervised injury prediction, which depends on reliable injury labels.In practice, such labels are difficult to obtain: video evidence is often ambiguous (occlusion,viewpoint limits), and true injury events are rare and cannot be safely staged, leading to noisysupervision. We address this problem with PHARL (PHysics-aware Alignment RepresentationLearning), which learns physically meaningful fall representations without requiring clinicaloutcome labels. PHARL regularizes motion embeddings with two complementary constraints:(1) trajectory-level temporal consistency for stable representation learning, and (2) multi-classphysics alignment, where simulation-derived contact outcomes shape embedding geometry. Bypairing video windows with temporally aligned simulation descriptors, PHARL captures localimpact-relevant dynamics while keeping inference purely feed-forward. Experiments on fourpublic datasets show that PHARL consistently improves risk-aligned representation quality overvisual-only baselines while maintaining strong fall-detection performance. Notably, PHARL alsoexhibits zero-shot ordinality: an interpretable severity structure (Head > Trunk > Supported)emerges without explicit ordinal supervision.

Related papers

• Role-Break in Attention Heads: Understanding and Detecting Hallucinations in VLMs [49.743008490747094]
  Vision-Language Models (VLMs) remain prone to hallucinations, producing content that is inconsistent with or unsupported by the input image.<n>Under a unified head-level view, we find that hallucination-induced changes manifest as localized deviations from each head's faithful contextual behavior.<n> Detailed analysis reveals that these deviations are systematically organized across attention heads, contextual sources, and deviation directions, and that the resulting signal is linearly readable once head identity is preserved.
  arXiv  Detail & Related papers  (2026-07-31T13:33:51Z)
• Unsupervised Keypoints for Real-Time Fall Detection: Comparative Analysis Under Real-world Conditions with Predictive Bandwidth Reduction [0.5959007032504439]
  Video captures fall-related posture and motion, yet deployment is limited by privacy, computation, and bandwidth.<n>We propose a privacy-preserving framework that replaces RGB transmission with compact motion representations based on unsupervised keypoints and predictive temporal modeling.<n>We evaluate the framework on the UR Fall Detection and Human Fall datasets using random, subject-disjoint, and occlusion-based splits.
  arXiv  Detail & Related papers  (2026-07-16T18:58:43Z)
• See Only When Needed: Context-Aware Attention Intervention for Mitigating Hallucinations in LVLMs [81.71384150441163]
  We propose Context-aware Attention Intervention (CAI) for large vision-language models (LVLMs)<n>CAI enforces a see only when needed principle via two-axis selectivity: where to look and when to intervene.<n> experiments across multiple LVLM backbones and benchmarks show that CAI achieves state-of-the-art hallucination mitigation.
  arXiv  Detail & Related papers  (2026-06-29T06:35:47Z)
• Neural Uncertainty Principle: A Unified View of Adversarial Fragility and LLM Hallucination [60.197429875410286]
  Adversarial vulnerability in vision and hallucination in large language models are conventionally viewed as separate problems.<n>Formalizing a Neural Uncertainty Principle (NUP) under a loss-induced state, we find that in near-bound regimes, further compression must be accompanied by increased sensitivity dispersion.<n>In vision, masking highly coupled components improves robustness without costly adversarial training.<n>In language, the same prefill-stage probe detects hallucination risk before generating any answer tokens.
  arXiv  Detail & Related papers  (2026-03-20T02:07:10Z)
• INFACT: A Diagnostic Benchmark for Induced Faithfulness and Factuality Hallucinations in Video-LLMs [69.11382230669491]
  hallucinations are outputs that contradict either video evidence (faithfulness) or verifiable world knowledge (factuality)<n>textscINFACT evaluates models in four modes: Base (clean), Visual Degradation, Evidence, and Temporal Intervention for order-sensitive items.<n>Experiments on 14 representative Video-LLMs reveal that higher Base-mode accuracy does not reliably translate to higher reliability in the induced modes.
  arXiv  Detail & Related papers  (2026-03-12T03:03:16Z)
• Evaluating Few-Shot Pill Recognition Under Visual Domain Shift [0.0]
  This study investigates few-shot pill recognition from a deployment-oriented perspective.<n>A two-stage object detection framework is employed, involving base training followed by few-shot fine-tuning.<n>Models trained on visually realistic, multi-pill data consistently exhibit greater robustness in low-shot scenarios.
  arXiv  Detail & Related papers  (2026-03-11T14:40:55Z)
• Weakly Supervised Patch Annotation for Improved Screening of Diabetic Retinopathy [9.215451885169538]
  Diabetic Retinopathy (DR) requires timely screening to prevent irreversible vision loss.<n>Existing literature primarily focuses on image-level supervision, weakly-supervised localization, and clustering-based representation learning.<n>We introduce Similarity-based.<n>enclosure via Feature-space Ensemble (SAFE), a two-stage framework that unifies weak supervision,.<n>contrastive learning, and patch-wise embedding inference.
  arXiv  Detail & Related papers  (2026-03-04T12:35:55Z)
• Same Answer, Different Representations: Hidden instability in VLMs [65.36933543377346]
  We introduce a representation-aware and frequency-aware evaluation framework that measures internal embedding drift, spectral sensitivity, and structural smoothness.<n>We apply this framework to modern Vision Language Models (VLMs) across the SEEDBench, MMMU, and POPE datasets.
  arXiv  Detail & Related papers  (2026-02-06T12:24:26Z)
• Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures [70.48661957773449]
  Emergent Misalignment refers to a failure mode in which fine-tuning large language models on narrowly scoped data induces broadly misaligned behavior.<n>Across multiple domains and model families, we find that fine-tuning models on data exhibiting specific character-level dispositions induces substantially stronger and more transferable misalignment than incorrect-advice fine-tuning.
  arXiv  Detail & Related papers  (2026-01-30T15:28:42Z)
• Hallucination Begins Where Saliency Drops [18.189047289404325]
  hallucinations frequently arise when preceding output tokens exhibit low saliency toward the prediction of the next token.<n>We introduce LVLMs-Saliency, a gradient-aware diagnostic framework that quantifies the visual grounding strength of each output token.<n>Our method significantly reduces hallucination rates while preserving fluency and task performance, offering a robust and interpretable solution.
  arXiv  Detail & Related papers  (2026-01-28T05:50:52Z)
• Assessing Situational and Spatial Awareness of VLMs with Synthetically Generated Video [18.381850705061]
  We introduce a synthetic benchmark that probes two complementary skills: situational awareness and spatial awareness.<n>We test three challenges: distinguishing violence from benign activity, binding assailant roles across viewpoints, and judging fine-grained trajectory alignment.<n>Results show performance only slightly above chance across tasks.
  arXiv  Detail & Related papers  (2026-01-22T09:14:11Z)
• DefVINS: Visual-Inertial Odometry for Deformable Scenes [14.028399155214068]
  Deformable scenes violate the rigidity assumptions underpinning visual-inertial odometry.<n>We introduce DefVINS, a visual-inertial odometry framework that separates a rigid, IMU-anchored state from a non-rigid warp.
  arXiv  Detail & Related papers  (2026-01-02T14:40:33Z)
• Nonparametric Identifiability of Causal Representations from Unknown Interventions [63.1354734978244]
  We study causal representation learning, the task of inferring latent causal variables and their causal relations from mixtures of the variables. Our goal is to identify both the ground truth latents and their causal graph up to a set of ambiguities which we show to be irresolvable from interventional data.
  arXiv  Detail & Related papers  (2023-06-01T10:51:58Z)
• Weakly-Supervised Cross-Domain Adaptation for Endoscopic Lesions Segmentation [79.58311369297635]
  We propose a new weakly-supervised lesions transfer framework, which can explore transferable domain-invariant knowledge across different datasets. A Wasserstein quantified transferability framework is developed to highlight widerange transferable contextual dependencies. A novel self-supervised pseudo label generator is designed to equally provide confident pseudo pixel labels for both hard-to-transfer and easy-to-transfer target samples.
  arXiv  Detail & Related papers  (2020-12-08T02:26:03Z)

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.