AI Paper Atlas

Research map / Video / Action recognition

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

Hao Zheng, Regina Lee, Yuqian Lu

NeurIPS 2023 · Video › Action recognition · approach: Action anticipation and latent actions · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fuse features from three camera views instead of single view (ablation)BCN · HA-ViD action segmentation, primitive taskAcc: 44 -> 47.2Improved
fuse features from three camera views instead of single view (ablation)MViTv2 · HA-ViD action recognition, atomic actionTop-1: 46.6 -> 50.8Improved
fuse features from three camera views instead of single view (ablation)BCN · HA-ViD action segmentation, atomic actionF1: 20.9 -> 41.7Improved
atomic action level instead of primitive task levelaction recognition · HA-ViDTop-1: 15.6% lower on averageHurt
right hand instead of left handatomic action recognition · HA-ViDTop-1: 2.4% lowerHurt
atomic action level instead of primitive task levelaction segmentation · HA-ViDAcc: 4% lower on averageHurt
DINO Swin-L instead of Faster-RCNN ResNext101object detection · HA-ViDAP: 22.2 -> 35.5Improved
ResNet101 backbone instead of ResNet50Faster-RCNN · HA-ViDAP: 21.7 -> 20.9No clear effect
YOLOv5-large instead of YOLOv5-smallYOLOv5 · HA-ViDAP: 10.2 -> 12.9Improved
ground truth boxes instead of DINO detectionsSORT · HA-ViD MOTMOTA: 20.4 -> 94.5Improved
ByteTrack instead of SORT with ground truth boxesMOT tracker · HA-ViD MOTIDS: 54.8 -> 121.6Hurt
ByteTrack instead of SORT with ground truth boxesMOT tracker · HA-ViD MOTMOTA: 94.5 -> 98.5Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy