AI Paper Atlas

Research map / 3D vision / Human pose estimation

CrossInfoNet: Multi-Task Information Sharing Based Hand Pose Estimation

Kuo Du, Xiangbo Lin, Yi Sun, Xiaohong Ma

CVPR 2019 · 3D vision › Human pose estimation · approach: Depth-based hand pose regression · 110 citations (OpenAlex)

Check 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
Add heat-map constraints to the baseline network (ablation)CrossInfoNet baseline · ICVLAverage 3D distance error (mm): 9.28 -> 9.08Improved
Add heat-map constraints to the baseline network (ablation)CrossInfoNet baseline · NYUAverage 3D distance error (mm): 11.17 -> 10.84Improved
Add cross-connections to the baseline with heat-map constraints (ablation)CrossInfoNet · ICVLAverage 3D distance error (mm): 9.08 -> 8.48Improved
Add cross-connections to the baseline with heat-map constraints (ablation)CrossInfoNet · NYUAverage 3D distance error (mm): 10.84 -> 10.08Improved
Add heat-map constraints to the cross-connection network (ablation)CrossInfoNet · ICVLAverage 3D distance error (mm): 8.79 -> 8.48Improved
Add heat-map constraints to the cross-connection network (ablation)CrossInfoNet · NYUAverage 3D distance error (mm): 10.57 -> 10.08Improved
Add cross-connections without heat-map constraints (ablation)CrossInfoNet baseline · ICVLAverage 3D distance error (mm): 9.28 -> 8.79Improved
Add cross-connections without heat-map constraints (ablation)CrossInfoNet baseline · NYUAverage 3D distance error (mm): 11.17 -> 10.57Improved
Use CrossInfoNet rather than Point-to-PointICVL depth-map hand pose estimation · ICVLMean error (mm): 6.3 -> 6.73Hurt
Use CrossInfoNet rather than V2VNYU hand pose estimation · NYUMean error (mm): 8.42 -> 10.08Hurt
Use CrossInfoNet rather than DenseRegMSRA hand pose estimation · MSRAMean error (mm): 7.2 -> 7.86Hurt
Use CrossInfoNet rather than DenseRegMSRA hand pose estimation · MSRAfps: 27.8 -> 124.5Improved

Later papers that compared with this method

3 later accepted papers report CrossInfoNet as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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