mlsanityData to 13 Oct 2026

SeqAug: Sequential Feature Resampling as a modality agnostic augmentation method

arXiv 2305.01954 ↗First posted 3 May 2023cs.CL cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Data augmentation is a prevalent technique for improving performance in various machine learning applications. We propose SeqAug, a modality-agnostic augmentation method that is tailored towards sequences of extracted features. The core idea of SeqAug is to augment the sequence by resampling from the underlying feature distribution. Resampling is performed by randomly selecting feature dimensions and permuting them along the temporal axis. Experiments on CMU-MOSEI verify that SeqAug is modality agnostic; it can be successfully applied to a single modality or multiple modalities. We further verify its compatibility with both recurrent and transformer architectures, and also demonstrate comparable to state-of-the-art results.

Key facts. Cited by 3 papers in the map (data through 13 Oct 2026). Builds on 14 of its 24 references that are in the map. First posted on arXiv 3 May 2023.

Builds on

14 of 24 references.

References · 14

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,170
  3. 2013Auto-Encoding Variational Bayescited by 4,024
  4. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,882
  5. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,542
  6. 2019Multimodal Transformer for Unaligned Multimodal Language Sequencescited by 639
  7. 2018Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approachcited by 119
  8. 2022UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognitioncited by 61
  9. 2016Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activationscited by 54
  10. 2022M-SENA: An Integrated Platform for Multimodal Sentiment Analysiscited by 21
  11. 2021Learning Multimodal VAEs through Mutual Supervisioncited by 18
  12. 2022A Data-Augmentation Is Worth A Thousand Samples: Exact Quantification From Analytical Augmented Sample Momentscited by 14
2 more
  1. 2022MMLatch: Bottom-up Top-down Fusion for Multimodal Sentiment Analysiscited by 6
  2. 2019MMGAN: Generative Adversarial Networks for Multi-Modal Distributionscited by 4

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025DeepMLF: Multimodal language model with learnable tokens for deep fusion in sentiment analysiscited by 3
  2. 2025Enhancing Speech Emotion Recognition with Graph-Based Multimodal Fusion and Prosodic Features for the Speech Emotion Recognition in Naturalistic Conditions Challenge at Interspeech 2025cited by 0
  3. 2026Segregate, Refine, Integrate: Decomposing Multimodal Fusion for Sentiment Analysiscited by 0