AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Hierarchical Contrast for Unsupervised Skeleton-Based Action Representation Learning

Jianfeng Dong, Shengkai Sun, Zhonglin Liu, Shujie Chen, Baolong Liu, Xun Wang

AAAI 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 63 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
use hierarchical contrast across instance, domain, clip, and part levels instead of instance-only contrast (ablation)HiCo-Transformer · NTU-60 x-sub; action recognitiontop-1 accuracy: 79.8 -> 81.1Improved
add domain-level contrast to instance-level contrast (ablation)HiCo-Transformer · NTU-60 x-sub; action recognitiontop-1 accuracy: 79.8 -> 80.7Improved
add clip/part-level contrast to instance and domain contrast (ablation)HiCo-Transformer · NTU-60 x-sub; action recognitiontop-1 accuracy: 80.7 -> 81.1Improved
jointly use temporal and spatial branches rather than either branch alone (ablation)HiCo-Transformer · NTU-60 x-sub; action recognitiontop-1 accuracy: 78.0 -> 79.8; 76.1 -> 79.8Improved
replace max-pooling with mean-pooling in UDM (ablation)HiCo-Transformer · NTU-60 x-sub; action recognitiontop-1 accuracy: 81.1 -> 80.8No clear effect
include Conv1d in UDM rather than remove it (ablation)HiCo-Transformer · NTU-60 x-sub; action recognitiontop-1 accuracy: 79.7 -> 81.1Improved
use concatenation rather than element-wise sum for branch fusion (ablation)HiCo-Transformer · NTU-60 x-sub; action recognitiontop-1 accuracy: 80.6 -> 81.1Improved
use concatenation rather than Hadamard product for branch fusion (ablation)HiCo-Transformer · NTU-60 x-sub; action recognitiontop-1 accuracy: 79.8 -> 81.1Improved
use concatenation rather than weighted sum for branch fusion (ablation)HiCo-Transformer · NTU-60 x-sub; action recognitiontop-1 accuracy: 80.7 -> 81.1Improved
increase the number of temporal and spatial granularities (ablation)HiCo · NTU-60 action recognitiontop-1 accuracyImproved
use HiCo rather than prior unsupervised methodsskeleton action recognition representation learning · PKU-MMD II x-subtop-1 accuracy: 38.5* -> 54.7Improved
fine-tune HiCo-Transformer rather than the prior methods from NTU-60action representation transfer to PKU-MMD II · PKU-MMD II x-sub; source NTU-60top-1 accuracy: 45.9 -> 56.3Improved

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