MHPR: Multidimensional Human Perception and Reasoning Benchmark for Large Vision-Languate Models

• URL: http://arxiv.org/abs/2605.03485v1
• Date: Tue, 05 May 2026 08:20:48 GMT
• Title: MHPR: Multidimensional Human Perception and Reasoning Benchmark for Large Vision-Languate Models
• Abstract summary: We introduce MHPR, a benchmark for joint perception-reasoning over human-centric scenes.<n>MHPR comprises a multi-level data design-Captioned Raw Data (C-RD), Supervised Fine-Tuning Data (SFT-D), Reinforcement Learning Data (RL-D), and Test Data (T-D)<n>We evaluate state-of-the-art vision-language models on fine-grained attributes and high-level semantics.
• Score: 2.1348189297234685
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multidimensional human understanding is essential for real-world applications such as film analysis and virtual digital humans, yet current LVLM benchmarks largely focus on single-task settings and lack fine-grained, human-centric evaluation. In this work, we introduce MHPR, a comprehensive benchmark for joint perception-reasoning over human-centric scenes spanning individual, multi-person, and human-object interaction dimensions. MHPR comprises a multi-level data design-Captioned Raw Data (C-RD), Supervised Fine-Tuning Data (SFT-D), Reinforcement Learning Data (RL-D), and Test Data (T-D)-together with an automated caption/VQA generation pipeline (ACVG) that performs category-wise attribute decomposition, attribute-specific rewriting, and multi-model voting to ensure high-quality, scalable annotations. We evaluate state-of-the-art vision-language models on fine-grained attributes (appearance, clothing, pose, parts) and high-level semantics (social relations, action semantics, spatial relations, intent and functionality). Our findings show that: 1) format-aligned SFT data substantially improves instruction following and stability; 2) challenge-focused RL data derived from bad-case analysis further enhances perception and reasoning on difficult instances; and 3) training Qwen2.5-VL-7B with MHPR yields significant gains, achieving near-parity with considerably larger models. We release ACVG and MHPR to facilitate reproducible, extensible research on human-centric perception and reasoning.

Related papers

• SAM 3D Body: Robust Full-Body Human Mesh Recovery [65.0108906331903]
  We introduce SAM 3D Body (3DB), a promptable model for single-image full-body 3D human mesh recovery (HMR)<n>3DB estimates the human pose of the body, feet, and hands.<n>It is the first model to use a new parametric mesh representation, Momentum Human Rig (MHR), which decouples skeletal structure and surface shape.
  arXiv  Detail & Related papers  (2026-02-17T20:26:37Z)
• Long Grounded Thoughts: Distilling Compositional Visual Reasoning Chains at Scale [70.23466957404891]
  We introduce a new reasoning data generation framework spanning diverse skills and levels of complexity with over 1M high-quality synthetic vision-centric questions.<n>We show that finetuning Qwen2.5-VL-7B on our data outperforms all open-data baselines across all evaluated vision-centric benchmarks.
  arXiv  Detail & Related papers  (2025-11-07T20:50:54Z)
• Human-MME: A Holistic Evaluation Benchmark for Human-Centric Multimodal Large Language Models [118.44328586173556]
  Multimodal Large Language Models (MLLMs) have demonstrated significant advances in visual understanding tasks.<n>Human-MME is a curated benchmark designed to provide a more holistic evaluation of MLLMs in human-centric scene understanding.<n>Our benchmark extends the single-target understanding to the multi-person and multi-image mutual understanding.
  arXiv  Detail & Related papers  (2025-09-30T12:20:57Z)
• HumanVideo-MME: Benchmarking MLLMs for Human-Centric Video Understanding [120.84817886550765]
  Multimodal Large Language Models (MLLMs) have demonstrated significant advances in visual understanding tasks involving both images and videos.<n>Existing human-centric benchmarks predominantly emphasize video generation quality and action recognition, while overlooking essential perceptual and cognitive abilities required in human-centered scenarios.<n>We propose a rigorously curated benchmark designed to provide a more holistic evaluation of MLLMs in human-centric video understanding.
  arXiv  Detail & Related papers  (2025-07-07T11:52:24Z)
• LLaVA-Pose: Enhancing Human Pose and Action Understanding via Keypoint-Integrated Instruction Tuning [1.820765907065129]
  Current vision-language models (VLMs) are well-adapted for general visual understanding tasks.<n>We introduce a method for generating such data by integrating human keypoints with traditional visual features such as captions and bounding boxes.<n>We fine-tune the LLaVA-1.5-7B model using this dataset and evaluate our resulting LLaVA-Pose model on the benchmark, achieving significant improvements.
  arXiv  Detail & Related papers  (2025-06-26T14:32:56Z)
• VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment [55.7956150385255]
  We investigate the efficacy of AI feedback to scale supervision for aligning vision-language models. We introduce VLFeedback, the first large-scale vision-language feedback dataset. We train Silkie, an LVLM fine-tuned via direct preference optimization on VLFeedback.
  arXiv  Detail & Related papers  (2024-10-12T07:56:47Z)
• Keypoint-Integrated Instruction-Following Data Generation for Enhanced Human Pose and Action Understanding in Multimodal Models [1.9890559505377343]
  Current vision-language multimodal models are well-adapted for general visual understanding tasks.<n>We introduce a method for generating such data by integrating human keypoints with traditional visual features such as captions and bounding boxes.<n>We fine-tune the LLaVA-1.5-7B model using this dataset and evaluate it on the benchmark, achieving significant improvements.
  arXiv  Detail & Related papers  (2024-09-14T05:07:57Z)
• Towards Adaptive Human-centric Video Anomaly Detection: A Comprehensive Framework and A New Benchmark [2.473948454680334]
  Human-centric Video Anomaly Detection (VAD) aims to identify human behaviors that deviate from normal.<n>We introduce the HuVAD (Human-centric privacy-enhanced Video Anomaly Detection) dataset and a novel Unsupervised Continual Anomaly Learning framework.
  arXiv  Detail & Related papers  (2024-08-26T14:55:23Z)
• StyleGAN-Human: A Data-Centric Odyssey of Human Generation [96.7080874757475]
  This work takes a data-centric perspective and investigates multiple critical aspects in "data engineering" We collect and annotate a large-scale human image dataset with over 230K samples capturing diverse poses and textures. We rigorously investigate three essential factors in data engineering for StyleGAN-based human generation, namely data size, data distribution, and data alignment.
  arXiv  Detail & Related papers  (2022-04-25T17:55:08Z)

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.