# Soften the Mask: Adaptive Temporal Soft Mask for Efficient Dynamic Facial Expression Recognition

arXiv: https://arxiv.org/abs/2502.21004 · HTML: https://mlsanity.com/paper/2502.21004/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 32 references that are in the map.
- First posted on arXiv 28 Feb 2025.

## Builds on (most cited first, 24 of 24)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations](https://mlsanity.com/paper/2202.07800/) (2022)
- [Deep Facial Expression Recognition: A Survey](https://mlsanity.com/paper/1804.08348/) (2018)
- [DFEW: A Large-Scale Database for Recognizing Dynamic Facial Expressions in the Wild](https://mlsanity.com/paper/2008.05924/) (2020)
- [Adaptive Focus for Efficient Video Recognition](https://mlsanity.com/paper/2105.03245/) (2021)
- [FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos](https://mlsanity.com/paper/2203.09463/) (2022)
- [MAFW: A Large-scale, Multi-modal, Compound Affective Database for Dynamic Facial Expression Recognition in the Wild](https://mlsanity.com/paper/2208.00847/) (2022)
- [Prompting Visual-Language Models for Dynamic Facial Expression Recognition](https://mlsanity.com/paper/2308.13382/) (2023)
- [MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition](https://mlsanity.com/paper/2307.02227/) (2023)
- [Intensity-Aware Loss for Dynamic Facial Expression Recognition in the Wild](https://mlsanity.com/paper/2208.10335/) (2022)
- [AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition](https://mlsanity.com/paper/2112.14238/) (2021)
- [EmoCLIP: A Vision-Language Method for Zero-Shot Video Facial Expression Recognition](https://mlsanity.com/paper/2310.16640/) (2023)
- [HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition](https://mlsanity.com/paper/2401.05698/) (2024)
- [CLIPER: A Unified Vision-Language Framework for In-the-Wild Facial Expression Recognition](https://mlsanity.com/paper/2303.00193/) (2023)
- [2D or not 2D? Adaptive 3D Convolution Selection for Efficient Video Recognition](https://mlsanity.com/paper/2012.14950/) (2020)
- [SupMAE: Supervised Masked Autoencoders Are Efficient Vision Learners](https://mlsanity.com/paper/2205.14540/) (2022)
- [SVFAP: Self-supervised Video Facial Affect Perceiver](https://mlsanity.com/paper/2401.00416/) (2023)
- [A3lign-DFER: Pioneering Comprehensive Dynamic Affective Alignment for Dynamic Facial Expression Recognition with CLIP](https://mlsanity.com/paper/2403.04294/) (2024)
- [MMA-DFER: MultiModal Adaptation of unimodal models for Dynamic Facial Expression Recognition in-the-wild](https://mlsanity.com/paper/2404.09010/) (2024)

## Abstract (arXiv)

Dynamic Facial Expression Recognition (DFER) facilitates the understanding of psychological intentions through non-verbal communication. Existing methods struggle to manage irrelevant information, such as background noise and redundant semantics, which impacts both efficiency and effectiveness. In this work, we propose a novel supervised temporal soft masked autoencoder network for DFER, namely AdaTosk, which integrates a parallel supervised classification branch with the self-supervised reconstruction branch. The self-supervised reconstruction branch applies random binary hard mask to generate diverse training samples, encouraging meaningful feature representations in visible tokens. Meanwhile the classification branch employs an adaptive temporal soft mask to flexibly mask visible tokens based on their temporal significance. Its two key components, respectively of, class-agnostic and class-semantic soft masks, serve to enhance critical expression moments and reduce semantic redundancy over time. Extensive experiments conducted on widely-used benchmarks demonstrate that our AdaTosk remarkably reduces computational costs compared with current state-of-the-art methods while still maintaining competitive performance.