# OmniQuery: Contextually Augmenting Captured Multimodal Memory to Enable Personal Question Answering

arXiv: https://arxiv.org/abs/2409.08250 · HTML: https://mlsanity.com/paper/2409.08250/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 80 references that are in the map.
- First posted on arXiv 12 Sep 2024.

## Builds on (most cited first, 30 of 32)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023)
- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering](https://mlsanity.com/paper/2104.06378/) (2021)
- [VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding](https://mlsanity.com/paper/2403.11481/) (2024)
- [MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text](https://mlsanity.com/paper/2210.02928/) (2022)
- [MultiModalQA: Complex Question Answering over Text, Tables and Images](https://mlsanity.com/paper/2104.06039/) (2021)
- [Multi-hop Question Answering](https://mlsanity.com/paper/2204.09140/) (2022)
- [Don't Forget to Connect! Improving RAG with Graph-based Reranking](https://mlsanity.com/paper/2405.18414/) (2024)
- [GazePointAR: A Context-Aware Multimodal Voice Assistant for Pronoun Disambiguation in Wearable Augmented Reality](https://mlsanity.com/paper/2404.08213/) (2024)
- [Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences](https://mlsanity.com/paper/2310.04621/) (2023)
- [GroundNLQ @ Ego4D Natural Language Queries Challenge 2023](https://mlsanity.com/paper/2306.15255/) (2023)
- [Memoro: Using Large Language Models to Realize a Concise Interface for Real-Time Memory Augmentation](https://mlsanity.com/paper/2403.02135/) (2024)
- [MPMQA: Multimodal Question Answering on Product Manuals](https://mlsanity.com/paper/2304.09660/) (2023)
- [OmniActions: Predicting Digital Actions in Response to Real-World Multimodal Sensory Inputs with LLMs](https://mlsanity.com/paper/2405.03901/) (2024)
- [A Contextual Inquiry of People with Vision Impairments in Cooking](https://mlsanity.com/paper/2402.15108/) (2024)

## Built on by (most cited first, 10 of 10)

- [Creating General User Models from Computer Use](https://mlsanity.com/paper/2505.10831/) (2025)
- [According to Me: Long-Term Personalized Referential Memory QA](https://mlsanity.com/paper/2603.01990/) (2026)
- [A Grounded Memory System For Smart Personal Assistants](https://mlsanity.com/paper/2505.06328/) (2025)
- [SpeechLess: Micro-utterance with Personalized Spatial Memory-aware Assistant in Everyday Augmented Reality](https://mlsanity.com/paper/2602.00793/) (2026)
- [Memento: Towards Proactive Visualization of Everyday Memories with Personal Wearable AR Assistant](https://mlsanity.com/paper/2601.17622/) (2026)
- [From Speech-to-Spatial: Grounding Utterances on A Live Shared View with Augmented Reality](https://mlsanity.com/paper/2602.03059/) (2026)
- [Life-Bench: A Benchmark and Knowledge Graph Framework for Multimodal Personalization Beyond Concept Recognition](https://mlsanity.com/paper/2602.19001/) (2026)
- [AdaDINO: Context-Adaptive DINO-Distilled Vision Foundation Models for Efficient Open-Vocabulary Edge Inference](https://mlsanity.com/paper/2604.15622/) (2026)
- [Activity Frames: Deterministic Screen-Activity Compilation for Agent Memory and Replay](https://mlsanity.com/paper/2608.05784/) (2026)
- [To Memories and Beyond: From Remembering to Knowing You across Long-Term Multimodal Personal Archives](https://mlsanity.com/paper/2609.19167/) (2026)

## Abstract (arXiv)

People often capture memories through photos, screenshots, and videos. While existing AI-based tools enable querying this data using natural language, they only support retrieving individual pieces of information like certain objects in photos, and struggle with answering more complex queries that involve interpreting interconnected memories like sequential events. We conducted a one-month diary study to collect realistic user queries and generated a taxonomy of necessary contextual information for integrating with captured memories. We then introduce OmniQuery, a novel system that is able to answer complex personal memory-related questions that require extracting and inferring contextual information. OmniQuery augments individual captured memories through integrating scattered contextual information from multiple interconnected memories. Given a question, OmniQuery retrieves relevant augmented memories and uses a large language model (LLM) to generate answers with references. In human evaluations, we show the effectiveness of OmniQuery with an accuracy of 71.5%, outperforming a conventional RAG system by winning or tying for 74.5% of the time.