Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation Article Swipe

MAKE IMPACT

Wenhao Li , Mengyuan Liu , Hong Liu , Pichao Wang , Jialun Cai , Nicu Sebe · YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2311.12028

Transformers have been successfully applied in the field of video-based 3D human pose estimation. However, the high computational costs of these video pose transformers (VPTs) make them impractical on resource-constrained devices. In this paper, we present a plug-and-play pruning-and-recovering framework, called Hourglass Tokenizer (HoT), for efficient transformer-based 3D human pose estimation from videos. Our HoT begins with pruning pose tokens of redundant frames and ends with recovering full-length tokens, resulting in a few pose tokens in the intermediate transformer blocks and thus improving the model efficiency. To effectively achieve this, we propose a token pruning cluster (TPC) that dynamically selects a few representative tokens with high semantic diversity while eliminating the redundancy of video frames. In addition, we develop a token recovering attention (TRA) to restore the detailed spatio-temporal information based on the selected tokens, thereby expanding the network output to the original full-length temporal resolution for fast inference. Extensive experiments on two benchmark datasets (i.e., Human3.6M and MPI-INF-3DHP) demonstrate that our method can achieve both high efficiency and estimation accuracy compared to the original VPT models. For instance, applying to MotionBERT and MixSTE on Human3.6M, our HoT can save nearly 50% FLOPs without sacrificing accuracy and nearly 40% FLOPs with only 0.2% accuracy drop, respectively. Code and models are available at https://github.com/NationalGAILab/HoT.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2311.12028

PDF

https://arxiv.org/pdf/2311.12028

OA Status

green

Cited By

1

Related Works

10

OpenAlex ID

https://openalex.org/W4388926371

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4388926371

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2311.12028

Digital Object Identifier

Title

Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2023

Year of publication

Publication date

2023-11-20

Full publication date if available

Authors

Wenhao Li, Mengyuan Liu, Hong Liu, Pichao Wang, Jialun Cai, Nicu Sebe

List of authors in order

Landing page

https://arxiv.org/abs/2311.12028

Publisher landing page

PDF URL

https://arxiv.org/pdf/2311.12028

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2311.12028

Direct OA link when available

Concepts

Computer science, Security token, FLOPS, Transformer, Inference, Pose, Artificial intelligence, Redundancy (engineering), Parallel computing, Computer network, Voltage, Operating system, Physics, Quantum mechanics

Top concepts (fields/topics) attached by OpenAlex

Cited by

1

Total citation count in OpenAlex

Citations by year (recent)

2024: 1

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload