PTH-Net: Dynamic Facial Expression Recognition without Face Detection and Alignment
Open accessPreprint — published as 10.1109/tip.2024.3504298
The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Abstract
Pyramid Temporal Hierarchy Network (PTH-Net) is a new paradigm for dynamic facial expression recognition, applied directly to raw videos without face detection and alignment (FDA). The traditional paradigm initially employs FDA to extract facial regions from raw videos before recognition. The advantage of this paradigm lies in minimizing the impact of complex backgrounds. However, it inadvertently neglects valuable information, such as body movements. Additionally, being bound to FDA sacrifices flexibility. In contrast, PTH-Net distinguishes background and target at the feature level, preserves more critical information, and is an end-to-end network that is more flexible. Specifically, PTH-Net utilizes a pre-trained backbone to extract multiple generic features of video understanding at various temporal frequencies, forming pyramid features. Subsequently, through temporal hierarchy refinement—achieved via differential sharing and downsampling—PTH-Net refines key information under the supervision of multiple receptive fields with the temporal-frequency invariance of expressions. In addition, to solve the problem of containing numerous irrelevant frames in videos, PTH-Net incorporates a Temporal Hierarchy Refinement layer to aggregate information at different temporal granularities, enhancing its ability to distinguish target and non-target expressions. Notably, PTH-Net achieves more comprehensive and in-depth understanding by merging knowledge from both forward and reverse video sequences. PTH-Net excels across six challenging benchmarks with lower computational costs in comparison to preceding methods.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
Tong, Z., Song, Y., Wang, J., & Wang, L. (2022) · arXiv · doi:10.48550/arxiv.2203.12602 · Cited by 909
Metadata
- Authors
- Li, M., Zhang, X., Liao, T., Lin, S., & Xiao, G.
- Affiliations
- Wenzhou University (CN)
- Venue
- IEEE Transactions on Image Processing
- Published
- 2024-01-26
- Volume
- 34
- Pages
- 30-43
- ISSN
- 1057-7149 (ISSN-L)
- OpenAlex
- W4404809461
- Cited by
- 13
- References
- 1
- Citations by year
- 2026: 9 · 2025: 4
- FWCI
- 5.27
- Type
- journal article
- Language
- en
- Open access
- green
- doi.org
- Licence
- Locations
- IEEE Transactions on Image Processing (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Natural Science Foundation of China (U2033210, 62072223)
- Natural Science Foundation of Zhejiang Province (LDT23F02024F02)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Keywords
- dynamic facial expression recognition, body movement, parameter sharing, downsampling
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: PTH-Net: Dynamic Facial Expression Recognition without Face Detection and Alignment. https://app.cochat.ai/papers/10.36227/techrxiv.170630113.31834403/v1
- The paper
- Li, M., Zhang, X., Liao, T., Lin, S., & Xiao, G. (2024). PTH-Net: Dynamic Facial Expression Recognition without Face Detection and Alignment. IEEE Transactions on Image Processing. https://doi.org/10.36227/techrxiv.170630113.31834403/v1
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.