# FinCap: Topic-Aligned Captions for Short-Form Financial YouTube Videos

arXiv: https://arxiv.org/abs/2509.25745 · HTML: https://mlsanity.com/paper/2509.25745/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 30 of its 55 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Chart understanding and anomaly detection](https://mlsanity.com/mllm/chart-understanding-and-anomaly-detection/)

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

- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI](https://mlsanity.com/paper/2404.16006/) (2024)
- [Sequence to Sequence -- Video to Text](https://mlsanity.com/paper/1505.00487/) (2015)
- [CLIP-It! Language-Guided Video Summarization](https://mlsanity.com/paper/2107.00650/) (2021)
- [Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation](https://mlsanity.com/paper/2303.12112/) (2023)
- [Attention-Based Multimodal Fusion for Video Description](https://mlsanity.com/paper/1701.03126/) (2017)
- [MLLMs are Deeply Affected by Modality Bias](https://mlsanity.com/paper/2505.18657/) (2025)
- [EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matching](https://mlsanity.com/paper/2111.08919/) (2021)
- [LVD-2M: A Long-take Video Dataset with Temporally Dense Captions](https://mlsanity.com/paper/2410.10816/) (2024)
- [G-VEval: A Versatile Metric for Evaluating Image and Video Captions Using GPT-4o](https://mlsanity.com/paper/2412.13647/) (2024)
- [VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation](https://mlsanity.com/paper/2502.12782/) (2025)
- [Robust Multimodal Large Language Models Against Modality Conflict](https://mlsanity.com/paper/2507.07151/) (2025)
- [Beyond Surface Similarity: Detecting Subtle Semantic Shifts in Financial Narratives](https://mlsanity.com/paper/2403.14341/) (2024)
- [Shorts vs. Regular Videos on YouTube: A Comparative Analysis of User Engagement and Content Creation Trends](https://mlsanity.com/paper/2403.00454/) (2024)
- [3MASSIV: Multilingual, Multimodal and Multi-Aspect dataset of Social Media Short Videos](https://mlsanity.com/paper/2203.14456/) (2022)
- [Enhancing Multimodal LLM for Detailed and Accurate Video Captioning using Multi-Round Preference Optimization](https://mlsanity.com/paper/2410.06682/) (2024)
- [Prompting Video-Language Foundation Models with Domain-specific Fine-grained Heuristics for Video Question Answering](https://mlsanity.com/paper/2410.09380/) (2024)
- [Large-scale Pre-training for Grounded Video Caption Generation](https://mlsanity.com/paper/2503.10781/) (2025)
- [TemCoCo: Temporally Consistent Multi-modal Video Fusion with Visual-Semantic Collaboration](https://mlsanity.com/paper/2508.17817/) (2025)
- [Fusing Audio, Textual and Visual Features for Sentiment Analysis of News Videos](https://mlsanity.com/paper/1604.02612/) (2016)
- [Getting the subtext without the text: Scalable multimodal sentiment classification from visual and acoustic modalities](https://mlsanity.com/paper/1807.01122/) (2018)
- [Image Captioning via Dynamic Path Customization](https://mlsanity.com/paper/2406.00334/) (2024)
- [Language Modeling for the Future of Finance: A Survey into Metrics, Tasks, and Data Opportunities](https://mlsanity.com/paper/2504.07274/) (2025)
- [VideoConviction: A Multimodal Benchmark for Human Conviction and Stock Market Recommendations](https://mlsanity.com/paper/2507.08104/) (2025)
- [Words That Unite The World: A Unified Framework for Deciphering Central Bank Communications Globally](https://mlsanity.com/paper/2505.17048/) (2025)
- [Can Vision Language Models Understand Mimed Actions?](https://mlsanity.com/paper/2506.21586/) (2025)
- [Watch, Listen, Understand, Mislead: Tri-modal Adversarial Attacks on Short Videos for Content Appropriateness Evaluation](https://mlsanity.com/paper/2507.11968/) (2025)

## Built on by (most cited first, 2 of 2)

- [UniFinEval: Towards Unified Evaluation of Financial Multimodal Models across Text, Images and Videos](https://mlsanity.com/paper/2601.22162/) (2026)
- [IPO-Mine: A Toolkit and Dataset for Section-Structured Analysis of Long, Multimodal IPO Documents](https://mlsanity.com/paper/2605.28714/) (2026)

## Abstract (arXiv)

We evaluate multimodal large language models (MLLMs) for topic-aligned captioning in financial short-form videos (SVs) by testing joint reasoning over transcripts (T), audio (A), and video (V). Using 624 annotated YouTube SVs, we assess all seven modality combinations (T, A, V, TA, TV, AV, TAV) across five topics: main recommendation, sentiment analysis, video purpose, visual analysis, and financial entity recognition. Video alone performs strongly on four of five topics, underscoring its value for capturing visual context and effective cues such as emotions, gestures, and body language. Selective pairs such as TV or AV often surpass TAV, implying that too many modalities may introduce noise. These results establish the first baselines for financial short-form video captioning and illustrate the potential and challenges of grounding complex visual cues in this domain. All code and data can be found on our Github under the CC-BY-NC-SA 4.0 license.