HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding

• URL: http://arxiv.org/abs/2503.12955v1
• Date: Mon, 17 Mar 2025 09:10:50 GMT
• Title: HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding
• Authors: Jiahe Zhao, Ruibing Hou, Zejie Tian, Hong Chang, Shiguang Shan,
• Abstract summary: We propose a new task to benchmark human-in-scene understanding for embodied agents: Human-In-Scene Question Answering (HIS-QA)<n>HIS-QA requires the agent to comprehend human states and behaviors, reason about its surrounding environment, and answer human-related questions within the scene.<n>We present HIS-Bench, a multimodal benchmark that systematically evaluates HIS understanding across a broad spectrum.
• Score: 57.763735969891286
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose a new task to benchmark human-in-scene understanding for embodied agents: Human-In-Scene Question Answering (HIS-QA). Given a human motion within a 3D scene, HIS-QA requires the agent to comprehend human states and behaviors, reason about its surrounding environment, and answer human-related questions within the scene. To support this new task, we present HIS-Bench, a multimodal benchmark that systematically evaluates HIS understanding across a broad spectrum, from basic perception to commonsense reasoning and planning. Our evaluation of various vision-language models on HIS-Bench reveals significant limitations in their ability to handle HIS-QA tasks. To this end, we propose HIS-GPT, the first foundation model for HIS understanding. HIS-GPT integrates 3D scene context and human motion dynamics into large language models while incorporating specialized mechanisms to capture human-scene interactions. Extensive experiments demonstrate that HIS-GPT sets a new state-of-the-art on HIS-QA tasks. We hope this work inspires future research on human behavior analysis in 3D scenes, advancing embodied AI and world models.

Related papers

• A Human Digital Twin Architecture for Knowledge-based Interactions and Context-Aware Conversations [0.9580312063277943]
  Recent developments in Artificial Intelligence (AI) and Machine Learning (ML) are creating new opportunities for Human-Autonomy Teaming (HAT) We present a real-time Human Digital Twin (HDT) architecture that integrates Large Language Models (LLMs) for knowledge reporting, answering, and recommendation, embodied in a visual interface. The HDT acts as a visually and behaviorally realistic team member, integrated throughout the mission lifecycle, from training to deployment to after-action review.
  arXiv  Detail & Related papers  (2025-04-04T03:56:26Z)
• Visual Agentic AI for Spatial Reasoning with a Dynamic API [26.759236329608935]
  We introduce an agentic program synthesis approach to solve 3D spatial reasoning problems. Our method overcomes limitations of prior approaches that rely on a static, human-defined API. We show that our method outperforms prior zero-shot models for visual reasoning in 3D.
  arXiv  Detail & Related papers  (2025-02-10T18:59:35Z)
• Multimodal Sense-Informed Prediction of 3D Human Motions [16.71099574742631]
  This work introduces a novel multi-modal sense-informed motion prediction approach, which conditions high-fidelity generation on two modal information. The gaze information is regarded as the human intention, and combined with both motion and scene features, we construct a ternary intention-aware attention to supervise the generation. On two real-world benchmarks, the proposed method achieves state-of-the-art performance both in 3D human pose and trajectory prediction.
  arXiv  Detail & Related papers  (2024-05-05T12:38:10Z)
• Expressive Forecasting of 3D Whole-body Human Motions [38.93700642077312]
  We are the first to formulate a whole-body human pose forecasting framework. Our model involves two key constituents: cross-context alignment (XCA) and cross-context interaction (XCI) We conduct extensive experiments on a newly-introduced large-scale benchmark and achieve state-of-theart performance.
  arXiv  Detail & Related papers  (2023-12-19T09:09:46Z)
• ChatPose: Chatting about 3D Human Pose [47.70287492050979]
  ChatPose is a framework to understand and reason about 3D human poses from images or textual descriptions. Our work is motivated by the human ability to intuitively understand postures from a single image or a brief description.
  arXiv  Detail & Related papers  (2023-11-30T18:59:52Z)
• Enhancing HOI Detection with Contextual Cues from Large Vision-Language Models [56.257840490146]
  ConCue is a novel approach for improving visual feature extraction in HOI detection. We develop a transformer-based feature extraction module with a multi-tower architecture that integrates contextual cues into both instance and interaction detectors.
  arXiv  Detail & Related papers  (2023-11-26T09:11:32Z)
• Human-centric Scene Understanding for 3D Large-scale Scenarios [52.12727427303162]
  We present a large-scale multi-modal dataset for human-centric scene understanding, dubbed HuCenLife. Our HuCenLife can benefit many 3D perception tasks, such as segmentation, detection, action recognition, etc.
  arXiv  Detail & Related papers  (2023-07-26T08:40:46Z)
• ScanERU: Interactive 3D Visual Grounding based on Embodied Reference Understanding [67.21613160846299]
  Embodied Reference Understanding (ERU) is first designed for this concern. New dataset called ScanERU is constructed to evaluate the effectiveness of this idea.
  arXiv  Detail & Related papers  (2023-03-23T11:36:14Z)
• HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes [54.61610144668777]
  We present a novel scene-and-language conditioned generative model that can produce 3D human motions in 3D scenes. Our experiments demonstrate that our model generates diverse and semantically consistent human motions in 3D scenes.
  arXiv  Detail & Related papers  (2022-10-18T10:14:11Z)
• EgoTaskQA: Understanding Human Tasks in Egocentric Videos [89.9573084127155]
  EgoTaskQA benchmark provides home for crucial dimensions of task understanding through question-answering on real-world egocentric videos. We meticulously design questions that target the understanding of (1) action dependencies and effects, (2) intents and goals, and (3) agents' beliefs about others. We evaluate state-of-the-art video reasoning models on our benchmark and show their significant gaps between humans in understanding complex goal-oriented egocentric videos.
  arXiv  Detail & Related papers  (2022-10-08T05:49:05Z)
• 3D Neural Scene Representations for Visuomotor Control [78.79583457239836]
  We learn models for dynamic 3D scenes purely from 2D visual observations. A dynamics model, constructed over the learned representation space, enables visuomotor control for challenging manipulation tasks.
  arXiv  Detail & Related papers  (2021-07-08T17:49:37Z)

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.