paper-with-me

홈 › Papers

HA-ViD: A Human Assembly Video Dataset for Comprehensive Assembly Knowledge Understanding

2023-07-09 · NeurIPS 2023 11

Understanding comprehensive assembly knowledge from videos is critical for futuristic ultra-intelligent industry. To enable technological breakthrough, we present HA-ViD - the first human assembly video dataset that features representative industrial assembly scenarios, natural procedural knowledge acquisition process, and consistent human-robot shared annotations. Specifically, HA-ViD captures diverse collaboration patterns of real-world assembly, natural human behaviors and learning progression during assembly, and granulate action annotations to subject, action verb, manipulated object, target object, and tool. We provide 3222 multi-view, multi-modality videos (each video contains one assembly task), 1.5M frames, 96K temporal labels and 2M spatial labels. We benchmark four foundational video understanding tasks: action recognition, action segmentation, object detection and multi-object tracking. Importantly, we analyze their performance for comprehending knowledge in assembly progress, process efficiency, task collaboration, skill parameters and human intention. Details of HA-ViD is available at: https://iai-hrc.github.io/ha-vid.

📄 PDF Abstract BibTeX arXiv:2307.05721

Code (1)

iai-hrc/ha-vid 공식 구현

Tasks

Action RecognitionAction SegmentationMulti-Object TrackingObjectobject-detectionObject DetectionObject TrackingVideo Understanding

Similar Papers 제목 키워드 기반

IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos

2024-11-18 · Yunong Liu, Cristobal Eyzaguirre, Manling Li, Shubh Khanna 외

Shape assembly is a ubiquitous task in daily life, integral for constructing complex 3D structures like IKEA furniture. While significant progress has been made in developing autonomous agents for shape assembly, existin…

Pose EstimationSemantic SegmentationVideo Object SegmentationVideo Semantic Segmentation

ProMQA-Assembly: Multimodal Procedural QA Dataset on Assembly

2025-09-03 · Kimihiro Hasegawa, Wiradee Imrattanatrai, Masaki Asada, Susan Holm 외 arxiv

Assistants on assembly tasks show great potential to benefit humans ranging from helping with everyday tasks to interacting in industrial settings. However, evaluation resources in assembly activities are underexplored. …

A vision-based framework for human behavior understanding in industrial assembly lines

2024-09-25 · Konstantinos Papoutsakis, Nikolaos Bakalos, Konstantinos Fragkoulis, Athena Zacharia 외

This paper introduces a vision-based framework for capturing and understanding human behavior in industrial assembly lines, focusing on car door manufacturing. The framework leverages advanced computer vision techniques …

Action Analysis

Generative Timelines for Instructed Visual Assembly

2024-11-19 · Alejandro Pardo, Jui-Hsien Wang, Bernard Ghanem, Josef Sivic 외

The objective of this work is to manipulate visual timelines (e.g. a video) through natural language instructions, making complex timeline editing tasks accessible to non-expert or potentially even disabled users. We cal…

Language Modelling

ATTACH Dataset: Annotated Two-Handed Assembly Actions for Human Action Understanding

2023-04-17 · Dustin Aganian, Benedict Stephan, Markus Eisenbach, Corinna Stretz 외

With the emergence of collaborative robots (cobots), human-robot collaboration in industrial manufacturing is coming into focus. For a cobot to act autonomously and as an assistant, it must understand human actions durin…

Action DetectionAction RecognitionAction UnderstandingVocal Bursts Valence Prediction