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

Source: [HA-ViD: A Human Assembly Video Dataset for Comprehensive Assembly Knowledge Understanding](<https://www.sota2.com/research/paper/68fa70081e209131cea48bb1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-02T03:13:02.636Z

Authors: Hao Zheng, Regina Lee, Yuqian Lu

Published: 2023-07-09T08:44:46.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2307.05721>)

[PDF](<https://arxiv.org/pdf/2307.05721.pdf>)

[Implementation](<https://iai-hrc.github.io/ha-vid>)
