# Memory-Inspired Temporal Prompt Interaction for Text-Image Classification

arXiv: https://arxiv.org/abs/2401.14856 · HTML: https://mlsanity.com/paper/2401.14856/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 34 references that are in the map.
- First posted on arXiv 26 Jan 2024.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [GPT Understands, Too](https://mlsanity.com/paper/2103.10385/) (2021)
- [MaPLe: Multi-modal Prompt Learning](https://mlsanity.com/paper/2210.03117/) (2022)
- [Tensor Fusion Network for Multimodal Sentiment Analysis](https://mlsanity.com/paper/1707.07250/) (2017)
- [Attention Bottlenecks for Multimodal Fusion](https://mlsanity.com/paper/2107.00135/) (2021)
- [Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers](https://mlsanity.com/paper/2004.00849/) (2020)
- [MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2005.03545/) (2020)
- [Visual Entailment: A Novel Task for Fine-Grained Image Understanding](https://mlsanity.com/paper/1901.06706/) (2019)
- [Gated Multimodal Units for Information Fusion](https://mlsanity.com/paper/1702.01992/) (2017)
- [UniT: Multimodal Multitask Learning with a Unified Transformer](https://mlsanity.com/paper/2102.10772/) (2021)
- [Memory Fusion Network for Multi-view Sequential Learning](https://mlsanity.com/paper/1802.00927/) (2018)
- [MultiBench: Multiscale Benchmarks for Multimodal Representation Learning](https://mlsanity.com/paper/2107.07502/) (2021)
- [Supervised Multimodal Bitransformers for Classifying Images and Text](https://mlsanity.com/paper/1909.02950/) (2019)
- [CentralNet: a Multilayer Approach for Multimodal Fusion](https://mlsanity.com/paper/1808.07275/) (2018)
- [Dynamic Multimodal Fusion](https://mlsanity.com/paper/2204.00102/) (2022)
- [Contrastive Multimodal Fusion with TupleInfoNCE](https://mlsanity.com/paper/2107.02575/) (2021)
- [Hybrid Contrastive Learning of Tri-Modal Representation for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2109.01797/) (2021)
- [CubeMLP: An MLP-based Model for Multimodal Sentiment Analysis and Depression Estimation](https://mlsanity.com/paper/2207.14087/) (2022)
- [Visual Entailment Task for Visually-Grounded Language Learning](https://mlsanity.com/paper/1811.10582/) (2018)
- [Modular and Parameter-Efficient Multimodal Fusion with Prompting](https://mlsanity.com/paper/2203.08055/) (2022)
- [Efficient Multimodal Fusion via Interactive Prompting](https://mlsanity.com/paper/2304.06306/) (2023)
- [CLMLF:A Contrastive Learning and Multi-Layer Fusion Method for Multimodal Sentiment Detection](https://mlsanity.com/paper/2204.05515/) (2022)
- [A Theory of Relation Learning and Cross-domain Generalization](https://mlsanity.com/paper/1910.05065/) (2019)
- [Future-Aware Diverse Trends Framework for Recommendation](https://mlsanity.com/paper/2011.00422/) (2020)
- [HUSE: Hierarchical Universal Semantic Embeddings](https://mlsanity.com/paper/1911.05978/) (2019)

## Built on by (most cited first, 1 of 1)

- [Historical Test-time Prompt Tuning for Vision Foundation Models](https://mlsanity.com/paper/2410.20346/) (2024)

## Abstract (arXiv)

In recent years, large-scale pre-trained multimodal models (LMM) generally emerge to integrate the vision and language modalities, achieving considerable success in various natural language processing and computer vision tasks. The growing size of LMMs, however, results in a significant computational cost for fine-tuning these models for downstream tasks. Hence, prompt-based interaction strategy is studied to align modalities more efficiently. In this contex, we propose a novel prompt-based multimodal interaction strategy inspired by human memory strategy, namely Memory-Inspired Temporal Prompt Interaction (MITP). Our proposed method involves in two stages as in human memory strategy: the acquiring stage, and the consolidation and activation stage. We utilize temporal prompts on intermediate layers to imitate the acquiring stage, leverage similarity-based prompt interaction to imitate memory consolidation, and employ prompt generation strategy to imitate memory activation. The main strength of our paper is that we interact the prompt vectors on intermediate layers to leverage sufficient information exchange between modalities, with compressed trainable parameters and memory usage. We achieve competitive results on several datasets with relatively small memory usage and 2.0M of trainable parameters (about 1% of the pre-trained foundation model).