# Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering

arXiv: https://arxiv.org/abs/1904.04357 · HTML: https://mlsanity.com/paper/1904.04357/

## Key facts

- Cited by 146 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Apr 2019.

## Built on by (most cited first, 30 of 146)

- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions](https://mlsanity.com/paper/2105.08276/) (2021)
- [Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling](https://mlsanity.com/paper/2102.06183/) (2021)
- [Zero-Shot Video Question Answering via Frozen Bidirectional Language Models](https://mlsanity.com/paper/2206.08155/) (2022)
- [Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions](https://mlsanity.com/paper/2111.10337/) (2021)
- [Learning to Answer Questions in Dynamic Audio-Visual Scenarios](https://mlsanity.com/paper/2203.14072/) (2022)
- [VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling](https://mlsanity.com/paper/2111.12681/) (2021)
- [All in One: Exploring Unified Video-Language Pre-training](https://mlsanity.com/paper/2203.07303/) (2022)
- [Align and Prompt: Video-and-Language Pre-training with Entity Prompts](https://mlsanity.com/paper/2112.09583/) (2021)
- [EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone](https://mlsanity.com/paper/2307.05463/) (2023)
- [AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning](https://mlsanity.com/paper/2103.16002/) (2021)
- [EgoTaskQA: Understanding Human Tasks in Egocentric Videos](https://mlsanity.com/paper/2210.03929/) (2022)
- [MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection](https://mlsanity.com/paper/2103.04224/) (2021)
- [EgoLife: Towards Egocentric Life Assistant](https://mlsanity.com/paper/2503.03803/) (2025)
- [SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events](https://mlsanity.com/paper/2103.15538/) (2021)
- [Video Question Answering: Datasets, Algorithms and Challenges](https://mlsanity.com/paper/2203.01225/) (2022)
- [Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2107.13118/) (2021)
- [An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling](https://mlsanity.com/paper/2209.01540/) (2022)
- [Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning](https://mlsanity.com/paper/2103.16564/) (2021)
- [Video as Conditional Graph Hierarchy for Multi-Granular Question Answering](https://mlsanity.com/paper/2112.06197/) (2021)
- [Invariant Grounding for Video Question Answering](https://mlsanity.com/paper/2206.02349/) (2022)
- [Enriching Local and Global Contexts for Temporal Action Localization](https://mlsanity.com/paper/2107.12960/) (2021)
- [Video Graph Transformer for Video Question Answering](https://mlsanity.com/paper/2207.05342/) (2022)
- [DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)](https://mlsanity.com/paper/2401.08392/) (2024)
- [Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering](https://mlsanity.com/paper/2207.12647/) (2022)
- [Bridge to Answer: Structure-aware Graph Interaction Network for Video Question Answering](https://mlsanity.com/paper/2104.14085/) (2021)
- [Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language](https://mlsanity.com/paper/2110.15358/) (2021)
- [MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering](https://mlsanity.com/paper/2212.09522/) (2022)
- [CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios](https://mlsanity.com/paper/2403.04640/) (2024)
- [From Representation to Reasoning: Towards both Evidence and Commonsense Reasoning for Video Question-Answering](https://mlsanity.com/paper/2205.14895/) (2022)

## Abstract (arXiv)

In this paper, we propose a novel end-to-end trainable Video Question Answering (VideoQA) framework with three major components: 1) a new heterogeneous memory which can effectively learn global context information from appearance and motion features; 2) a redesigned question memory which helps understand the complex semantics of question and highlights queried subjects; and 3) a new multimodal fusion layer which performs multi-step reasoning by attending to relevant visual and textual hints with self-updated attention. Our VideoQA model firstly generates the global context-aware visual and textual features respectively by interacting current inputs with memory contents. After that, it makes the attentional fusion of the multimodal visual and textual representations to infer the correct answer. Multiple cycles of reasoning can be made to iteratively refine attention weights of the multimodal data and improve the final representation of the QA pair. Experimental results demonstrate our approach achieves state-of-the-art performance on four VideoQA benchmark datasets.