# Foundational Question Generation for Video Question Answering via an Embedding-Integrated Approach

arXiv: https://arxiv.org/abs/2511.17618 · HTML: https://mlsanity.com/paper/2511.17618/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 46 references that are in the map.
- First posted on arXiv 18 Nov 2025.

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text](https://mlsanity.com/paper/2104.11178/) (2021)
- [Asking and Answering Questions to Evaluate the Factual Consistency of Summaries](https://mlsanity.com/paper/2004.04228/) (2020)
- [Zero-Shot Video Question Answering via Frozen Bidirectional Language Models](https://mlsanity.com/paper/2206.08155/) (2022)
- [Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting](https://mlsanity.com/paper/2304.03307/) (2023)
- [GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph](https://mlsanity.com/paper/2309.13625/) (2023)
- [All You May Need for VQA are Image Captions](https://mlsanity.com/paper/2205.01883/) (2022)
- [Vamos: Versatile Action Models for Video Understanding](https://mlsanity.com/paper/2311.13627/) (2023)
- [ViLA: Efficient Video-Language Alignment for Video Question Answering](https://mlsanity.com/paper/2312.08367/) (2023)
- [Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer](https://mlsanity.com/paper/2308.08414/) (2023)
- [TE-TAD: Towards Full End-to-End Temporal Action Detection via Time-Aligned Coordinate Expression](https://mlsanity.com/paper/2404.02405/) (2024)
- [Empowering Large Language Model for Continual Video Question Answering with Collaborative Prompting](https://mlsanity.com/paper/2410.00771/) (2024)
- [A Practical Toolkit for Multilingual Question and Answer Generation](https://mlsanity.com/paper/2305.17416/) (2023)
- [SGSH: Stimulate Large Language Models with Skeleton Heuristics for Knowledge Base Question Generation](https://mlsanity.com/paper/2404.01923/) (2024)

## Abstract (arXiv)

Conventional VQA approaches primarily rely on question-answer (Q&A) pairs to learn the spatio-temporal dynamics of video content. However, most existing annotations are event-centric, which restricts the model's ability to capture the comprehensive context of a scene. The lack of fundamental information such as object categories, spatial configurations, and descriptive visual attributes prevents the model from forming a complete understanding of the environment, ultimately limiting its generalization and reasoning capability. In this paper, we introduce Foundational Question Generation for Video Question Answering via an Embedding-Integrated Approach (FIQ), a framework designed to enhance the reasoning capability of VQA models by improving their foundational comprehension of video content. FIQ generates Q&A pairs from descriptive information extracted directly from videos, thereby enriching the dataset with core scene-level attributes. These generated pairs help the model develop a more holistic understanding of the video, leading to improved generalizability and reasoning performance. In addition, we propose a VQ-CAlign module that aligns task-specific question embeddings with corresponding visual features, preserving essential contextual cues and enhancing adaptability to downstream tasks. Experimental results on the SUTD-TrafficQA dataset demonstrate that FIQ achieves state-of-the-art performance, surpassing existing baseline approaches.