AI Paper Atlas

Research map / 3D vision / Human pose estimation

H 2 OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers

Wenhao Li, Mengyuan Liu, Hong Liu, Pichao Wang, Shijian Lu, Nicu Sebe

TPAMI 2025 · 3D vision › Human pose estimation · approach: Temporal video pose estimation · 3 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
add H2OT hierarchical pruning and recoveringMixSTE (seq2seq) · Human3.6MMPJPE (mm): 40.9 -> 40.5Improved
add H2OT token pruningMixSTE (seq2seq) · Human3.6MFLOPs (G): 277.25 -> 118.23Improved
add H2OT token pruningMotionBERT (seq2seq) · Human3.6MMPJPE (mm): 39.8 -> 39.9No clear effect
replace HoT with H2OT (hierarchical, TPS and TRI)MixSTE · Human3.6MMPJPE (mm): 41.0 -> 40.5Improved
use sequence-sampler pruning with interpolation recovering instead of clustering with attention recovering (ablation)MixSTE · Human3.6MFPS per frame: 56 -> 66Improved
use motion-based pruning (TPMo) instead of clustering (TPC) (ablation)MixSTE · Human3.6MMPJPE (mm): 41.0 -> 42.8Hurt
use attention-based pruning (TPA) instead of clustering (TPC) (ablation)MixSTE · Human3.6MMPJPE (mm): 41.0 -> 42.1Hurt
add hierarchical second pruning stage r=[121,81] over single stage r=81 (ablation)MixSTE · Human3.6MMPJPE (mm): 41.0 -> 40.5Improved
prune more tokens (r=[121,27] instead of [121,81]) (ablation)MixSTE · Human3.6MMPJPE (mm): 40.5 -> 41.3Hurt
increase number of recovered tokens f from 9 to 243 (ablation)MixSTE (seq2frame) · Human3.6MMPJPE (mm): 41.2 -> 40.4Improved
add H2OT under 12.5 FPS input (ablation)MixSTE · Human3.6MMPJPE (mm): 39.2 -> 40.8Hurt
add H2OT under 50 FPS input (ablation)MixSTE · Human3.6MMPJPE (mm): 40.9 -> 40.5Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

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