# ScaleVLAD: Improving Multimodal Sentiment Analysis via Multi-Scale Fusion of Locally Descriptors

arXiv: https://arxiv.org/abs/2112.01368 · HTML: https://mlsanity.com/paper/2112.01368/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 51 references that are in the map.
- First posted on arXiv 2 Dec 2021.

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [Multimodal Transformer for Unaligned Multimodal Language Sequences](https://mlsanity.com/paper/1906.00295/) (2019)
- [Tensor Fusion Network for Multimodal Sentiment Analysis](https://mlsanity.com/paper/1707.07250/) (2017)
- [MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2005.03545/) (2020)
- [UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation](https://mlsanity.com/paper/2002.06353/) (2020)
- [Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition](https://mlsanity.com/paper/2103.01486/) (2021)
- [Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2102.04830/) (2021)
- [Memory Fusion Network for Multi-view Sequential Learning](https://mlsanity.com/paper/1802.00927/) (2018)
- [Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities](https://mlsanity.com/paper/1812.07809/) (2018)
- [T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval](https://mlsanity.com/paper/2104.10054/) (2021)
- [Multi-attention Recurrent Network for Human Communication Comprehension](https://mlsanity.com/paper/1802.00923/) (2018)
- [Words Can Shift: Dynamically Adjusting Word Representations Using Nonverbal Behaviors](https://mlsanity.com/paper/1811.09362/) (2018)
- [Multimodal Intelligence: Representation Learning, Information Fusion, and Applications](https://mlsanity.com/paper/1911.03977/) (2019)
- [Learning Relationships between Text, Audio, and Video via Deep Canonical Correlation for Multimodal Language Analysis](https://mlsanity.com/paper/1911.05544/) (2019)
- [Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research](https://mlsanity.com/paper/2005.00357/) (2020)
- [Modality to Modality Translation: An Adversarial Representation Learning and Graph Fusion Network for Multimodal Fusion](https://mlsanity.com/paper/1911.07848/) (2019)
- [Bi-Bimodal Modality Fusion for Correlation-Controlled Multimodal Sentiment Analysis](https://mlsanity.com/paper/2107.13669/) (2021)
- [Multimodal Language Analysis with Recurrent Multistage Fusion](https://mlsanity.com/paper/1808.03920/) (2018)
- [TransModality: An End2End Fusion Method with Transformer for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2009.02902/) (2020)
- [Multi-task Learning for Multi-modal Emotion Recognition and Sentiment Analysis](https://mlsanity.com/paper/1905.05812/) (2019)
- [Jointly Fine-Tuning "BERT-like" Self Supervised Models to Improve Multimodal Speech Emotion Recognition](https://mlsanity.com/paper/2008.06682/) (2020)
- [CM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learning](https://mlsanity.com/paper/1710.05106/) (2017)
- [Multimodal Affective Analysis Using Hierarchical Attention Strategy with Word-Level Alignment](https://mlsanity.com/paper/1805.08660/) (2018)

## Built on by (most cited first, 12 of 12)

- [UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition](https://mlsanity.com/paper/2211.11256/) (2022)
- [Make Acoustic and Visual Cues Matter: CH-SIMS v2.0 Dataset and AV-Mixup Consistent Module](https://mlsanity.com/paper/2209.02604/) (2022)
- [i-Code: An Integrative and Composable Multimodal Learning Framework](https://mlsanity.com/paper/2205.01818/) (2022)
- [UniSA: Unified Generative Framework for Sentiment Analysis](https://mlsanity.com/paper/2309.01339/) (2023)
- [Recent Advances in Multimodal Affective Computing: An NLP Perspective](https://mlsanity.com/paper/2409.07388/) (2024)
- [Unveiling the Cognitive Compass: Theory-of-Mind-Guided Multimodal Emotion Reasoning](https://mlsanity.com/paper/2602.00971/) (2026)
- [Noise-Resistant Multimodal Transformer for Emotion Recognition](https://mlsanity.com/paper/2305.02814/) (2023)
- [Denoising Bottleneck with Mutual Information Maximization for Video Multimodal Fusion](https://mlsanity.com/paper/2305.14652/) (2023)
- [Hierarchical Audio-Visual Information Fusion with Multi-label Joint Decoding for MER 2023](https://mlsanity.com/paper/2309.07925/) (2023)
- ["Yeah Right!" -- Do LLMs Exhibit Multimodal Feature Transfer?](https://mlsanity.com/paper/2501.04138/) (2025)
- [Rethinking Multimodal Sentiment Analysis: A High-Accuracy, Simplified Fusion Architecture](https://mlsanity.com/paper/2505.04642/) (2025)
- [Audio Sentiment Analysis via Distillation and Cross-Modal Integration of Generated Multilingual Transcripts](https://mlsanity.com/paper/2607.06611/) (2026)

## Abstract (arXiv)

Fusion technique is a key research topic in multimodal sentiment analysis. The recent attention-based fusion demonstrates advances over simple operation-based fusion. However, these fusion works adopt single-scale, i.e., token-level or utterance-level, unimodal representation. Such single-scale fusion is suboptimal because that different modality should be aligned with different granularities. This paper proposes a fusion model named ScaleVLAD to gather multi-Scale representation from text, video, and audio with shared Vectors of Locally Aggregated Descriptors to improve unaligned multimodal sentiment analysis. These shared vectors can be regarded as shared topics to align different modalities. In addition, we propose a self-supervised shifted clustering loss to keep the fused feature differentiation among samples. The backbones are three Transformer encoders corresponding to three modalities, and the aggregated features generated from the fusion module are feed to a Transformer plus a full connection to finish task predictions. Experiments on three popular sentiment analysis benchmarks, IEMOCAP, MOSI, and MOSEI, demonstrate significant gains over baselines.