# Align and Aggregate: Compositional Reasoning with Video Alignment and Answer Aggregation for Video Question-Answering

arXiv: https://arxiv.org/abs/2407.03008 · HTML: https://mlsanity.com/paper/2407.03008/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 39 of its 54 references that are in the map.
- First posted on arXiv 3 Jul 2024.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 30 of 39)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions](https://mlsanity.com/paper/2105.08276/) (2021)
- [Localizing Moments in Video with Natural Language](https://mlsanity.com/paper/1708.01641/) (2017)
- [TALL: Temporal Activity Localization via Language Query](https://mlsanity.com/paper/1705.02101/) (2017)
- [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](https://mlsanity.com/paper/1711.09577/) (2017)
- [TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering](https://mlsanity.com/paper/1704.04497/) (2017)
- [VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling](https://mlsanity.com/paper/2111.12681/) (2021)
- [Hierarchical Conditional Relation Networks for Video Question Answering](https://mlsanity.com/paper/2002.10698/) (2020)
- [Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering](https://mlsanity.com/paper/1904.04357/) (2019)
- [AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning](https://mlsanity.com/paper/2103.16002/) (2021)
- [Context-aware Biaffine Localizing Network for Temporal Sentence Grounding](https://mlsanity.com/paper/2103.11555/) (2021)
- [Motion-Appearance Co-Memory Networks for Video Question Answering](https://mlsanity.com/paper/1803.10906/) (2018)
- [Location-aware Graph Convolutional Networks for Video Question Answering](https://mlsanity.com/paper/2008.09105/) (2020)
- [An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling](https://mlsanity.com/paper/2209.01540/) (2022)
- [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)
- [Video Graph Transformer for Video Question Answering](https://mlsanity.com/paper/2207.05342/) (2022)
- [Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning](https://mlsanity.com/paper/2203.13049/) (2022)
- [Bridge to Answer: Structure-aware Graph Interaction Network for Video Question Answering](https://mlsanity.com/paper/2104.14085/) (2021)
- [From Representation to Reasoning: Towards both Evidence and Commonsense Reasoning for Video Question-Answering](https://mlsanity.com/paper/2205.14895/) (2022)
- [DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering](https://mlsanity.com/paper/2107.04768/) (2021)
- [(2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answering](https://mlsanity.com/paper/2202.09277/) (2022)

## Built on by (most cited first, 9 of 9)

- [Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)](https://mlsanity.com/paper/2504.03151/) (2025)
- [Eyes on the Road: State-of-the-Art Video Question Answering Models Assessment for Traffic Monitoring Tasks](https://mlsanity.com/paper/2412.01132/) (2024)
- [AViLA: Asynchronous Vision-Language Agent for Streaming Multimodal Data Interaction](https://mlsanity.com/paper/2506.18472/) (2025)
- [ViQAgent: Zero-Shot Video Question Answering via Agent with Open-Vocabulary Grounding Validation](https://mlsanity.com/paper/2505.15928/) (2025)
- [POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval](https://mlsanity.com/paper/2505.19189/) (2025)
- [Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning](https://mlsanity.com/paper/2506.07811/) (2025)
- [Reinforcing Consistency in Video MLLMs with Structured Rewards](https://mlsanity.com/paper/2604.01460/) (2026)
- [VSI: Visual Subtitle Integration for Keyframe Selection to enhance Long Video Understanding](https://mlsanity.com/paper/2508.06869/) (2025)
- [Video Flow as Time Series: Discovering Temporal Consistency and Variability for VideoQA](https://mlsanity.com/paper/2504.05783/) (2025)

## Abstract (arXiv)

Despite the recent progress made in Video Question-Answering (VideoQA), these methods typically function as black-boxes, making it difficult to understand their reasoning processes and perform consistent compositional reasoning. To address these challenges, we propose a textitmodel-agnostic Video Alignment and Answer Aggregation (VA3) framework, which is capable of enhancing both compositional consistency and accuracy of existing VidQA methods by integrating video aligner and answer aggregator modules. The video aligner hierarchically selects the relevant video clips based on the question, while the answer aggregator deduces the answer to the question based on its sub-questions, with compositional consistency ensured by the information flow along question decomposition graph and the contrastive learning strategy. We evaluate our framework on three settings of the AGQA-Decomp dataset with three baseline methods, and propose new metrics to measure the compositional consistency of VidQA methods more comprehensively. Moreover, we propose a large language model (LLM) based automatic question decomposition pipeline to apply our framework to any VidQA dataset. We extend MSVD and NExT-QA datasets with it to evaluate our VA3 framework on broader scenarios. Extensive experiments show that our framework improves both compositional consistency and accuracy of existing methods, leading to more interpretable real-world VidQA models.