# Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos

arXiv: https://arxiv.org/abs/2408.14469 · HTML: https://mlsanity.com/paper/2408.14469/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 26 Aug 2024.

## Builds on (most cited first, 23 of 23)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering](https://mlsanity.com/paper/1906.02467/) (2019)
- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding](https://mlsanity.com/paper/2312.02051/) (2023)
- [Perception Test: A Diagnostic Benchmark for Multimodal Video Models](https://mlsanity.com/paper/2305.13786/) (2023)
- [MovieQA: Understanding Stories in Movies through Question-Answering](https://mlsanity.com/paper/1512.02902/) (2015)
- [STAR: A Benchmark for Situated Reasoning in Real-World Videos](https://mlsanity.com/paper/2405.09711/) (2024)
- [UniVTG: Towards Unified Video-Language Temporal Grounding](https://mlsanity.com/paper/2307.16715/) (2023)
- [How2: A Large-scale Dataset for Multimodal Language Understanding](https://mlsanity.com/paper/1811.00347/) (2018)
- [Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning](https://mlsanity.com/paper/2402.11435/) (2024)
- [GROUNDHOG: Grounding Large Language Models to Holistic Segmentation](https://mlsanity.com/paper/2402.16846/) (2024)
- [Action Scene Graphs for Long-Form Understanding of Egocentric Videos](https://mlsanity.com/paper/2312.03391/) (2023)
- [NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory](https://mlsanity.com/paper/2301.00746/) (2023)
- [SnAG: Scalable and Accurate Video Grounding](https://mlsanity.com/paper/2404.02257/) (2024)
- [End-to-End Beam Retrieval for Multi-Hop Question Answering](https://mlsanity.com/paper/2308.08973/) (2023)
- [Are we asking the right questions in MovieQA?](https://mlsanity.com/paper/1911.03083/) (2019)

## Built on by (most cited first, 30 of 45)

- [Streaming Video Question-Answering with In-context Video KV-Cache Retrieval](https://mlsanity.com/paper/2503.00540/) (2025)
- [CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding](https://mlsanity.com/paper/2412.12075/) (2024)
- [BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding](https://mlsanity.com/paper/2503.21483/) (2025)
- [StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant](https://mlsanity.com/paper/2505.05467/) (2025)
- [LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant](https://mlsanity.com/paper/2503.03663/) (2025)
- [OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts](https://mlsanity.com/paper/2503.22952/) (2025)
- [VideoMind: A Chain-of-LoRA Agent for Temporal-Grounded Video Reasoning](https://mlsanity.com/paper/2503.13444/) (2025)
- [VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding](https://mlsanity.com/paper/2507.13353/) (2025)
- [Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)](https://mlsanity.com/paper/2504.03151/) (2025)
- [STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training](https://mlsanity.com/paper/2412.00161/) (2024)
- [A Survey on Video Temporal Grounding with Multimodal Large Language Model](https://mlsanity.com/paper/2508.10922/) (2025)
- [ECBench: Can Multi-modal Foundation Models Understand the Egocentric World? A Holistic Embodied Cognition Benchmark](https://mlsanity.com/paper/2501.05031/) (2025)
- [Object-centric Video Question Answering with Visual Grounding and Referring](https://mlsanity.com/paper/2507.19599/) (2025)
- [AdsQA: Towards Advertisement Video Understanding](https://mlsanity.com/paper/2509.08621/) (2025)
- [SocialGesture: Delving into Multi-person Gesture Understanding](https://mlsanity.com/paper/2504.02244/) (2025)
- [EASG-Bench: Video Q&A Benchmark with Egocentric Action Scene Graphs](https://mlsanity.com/paper/2506.05787/) (2025)
- [KFS-Bench: Comprehensive Evaluation of Key Frame Sampling in Long Video Understanding](https://mlsanity.com/paper/2512.14017/) (2025)
- [ENTER: Event Based Interpretable Reasoning for VideoQA](https://mlsanity.com/paper/2501.14194/) (2025)
- [VITED: Video Temporal Evidence Distillation](https://mlsanity.com/paper/2503.12855/) (2025)
- [ANNEXE: Unified Analyzing, Answering, and Pixel Grounding for Egocentric Interaction](https://mlsanity.com/paper/2504.01472/) (2025)
- [Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challenges](https://mlsanity.com/paper/2511.13261/) (2025)
- [EGOSTREAM: A Diagnostic Benchmark for Streaming Episodic Memory in Egocentric Vision](https://mlsanity.com/paper/2605.31557/) (2026)
- [Factorized Learning for Temporally Grounded Video-Language Models](https://mlsanity.com/paper/2512.24097/) (2025)
- [Interaction-aware Representation Modeling with Co-occurrence Consistency for Egocentric Hand-Object Parsing](https://mlsanity.com/paper/2602.20597/) (2026)
- [Native Active Perception as Reasoning for Omni-Modal Understanding](https://mlsanity.com/paper/2606.19341/) (2026)
- [EgoAVU: Egocentric Audio-Visual Understanding](https://mlsanity.com/paper/2602.06139/) (2026)
- [FocusGraph: Graph-Structured Frame Selection for Embodied Long Video Question Answering](https://mlsanity.com/paper/2603.04349/) (2026)
- [HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes](https://mlsanity.com/paper/2508.13692/) (2025)
- [EMCompress: Video-LLMs with Endomorphic Multimodal Compression](https://mlsanity.com/paper/2508.21094/) (2025)
- [MemoryCard: Topic-Aware Multi-Modal Clue Compression for Long-Video Question Answering](https://mlsanity.com/paper/2606.05917/) (2026)

## Abstract (arXiv)

This paper considers the problem of Multi-Hop Video Question Answering (MH-VidQA) in long-form egocentric videos. This task not only requires to answer visual questions, but also to localize multiple relevant time intervals within the video as visual evidences. We develop an automated pipeline to create multi-hop question-answering pairs with associated temporal evidence, enabling to construct a large-scale dataset for instruction-tuning. To monitor the progress of this new task, we further curate a high-quality benchmark, MultiHop-EgoQA, with careful manual verification and refinement. Experimental results reveal that existing multi-modal systems exhibit inadequate multi-hop grounding and reasoning abilities, resulting in unsatisfactory performance. We then propose a novel architecture, termed as Grounding Scattered Evidence with Large Language Model (GeLM), that enhances multi-modal large language models (MLLMs) by incorporating a grounding module to retrieve temporal evidence from videos using flexible grounding tokens. Trained on our visual instruction data, GeLM demonstrates improved multi-hop grounding and reasoning capabilities, setting a new baseline for this challenging task. Furthermore, when trained on third-person view videos, the same architecture also achieves state-of-the-art performance on the single-hop VidQA benchmark, ActivityNet-RTL, demonstrating its effectiveness.