mlsanityData to 14 Oct 2026

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

arXiv 2509.25745 ↗First posted 30 Sep 2025cs.CV cs.CL cs.MMcited by 2

On the map: Multimodal LLMs / vision-language models → Chart understanding and anomaly detection

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.

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.

Builds on

30 of 55 references.

References · 30

  1. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
  2. 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,046
  3. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,423
  4. 2014Show and Tell: A Neural Image Caption Generatorcited by 879
  5. 2024MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGIcited by 193
  6. 2015Sequence to Sequence -- Video to Textcited by 158
  7. 2021CLIP-It! Language-Guided Video Summarizationcited by 99
  8. 2023Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluationcited by 78
  9. 2017Attention-Based Multimodal Fusion for Video Descriptioncited by 75
  10. 2025MLLMs are Deeply Affected by Modality Biascited by 40
  11. 2021EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matchingcited by 36
  12. 2024LVD-2M: A Long-take Video Dataset with Temporally Dense Captionscited by 25
18 more
  1. 2024G-VEval: A Versatile Metric for Evaluating Image and Video Captions Using GPT-4ocited by 23
  2. 2025VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generationcited by 23
  3. 2025Robust Multimodal Large Language Models Against Modality Conflictcited by 18
  4. 2024Beyond Surface Similarity: Detecting Subtle Semantic Shifts in Financial Narrativescited by 13
  5. 2024Shorts vs. Regular Videos on YouTube: A Comparative Analysis of User Engagement and Content Creation Trendscited by 11
  6. 20223MASSIV: Multilingual, Multimodal and Multi-Aspect dataset of Social Media Short Videoscited by 8
  7. 2024Enhancing Multimodal LLM for Detailed and Accurate Video Captioning using Multi-Round Preference Optimizationcited by 8
  8. 2024Prompting Video-Language Foundation Models with Domain-specific Fine-grained Heuristics for Video Question Answeringcited by 5
  9. 2025Large-scale Pre-training for Grounded Video Caption Generationcited by 5
  10. 2025TemCoCo: Temporally Consistent Multi-modal Video Fusion with Visual-Semantic Collaborationcited by 5
  11. 2016Fusing Audio, Textual and Visual Features for Sentiment Analysis of News Videoscited by 4
  12. 2018Getting the subtext without the text: Scalable multimodal sentiment classification from visual and acoustic modalitiescited by 3
  13. 2024Image Captioning via Dynamic Path Customizationcited by 3
  14. 2025Language Modeling for the Future of Finance: A Survey into Metrics, Tasks, and Data Opportunitiescited by 3
  15. 2025VideoConviction: A Multimodal Benchmark for Human Conviction and Stock Market Recommendationscited by 3
  16. 2025Words That Unite The World: A Unified Framework for Deciphering Central Bank Communications Globallycited by 2
  17. 2025Can Vision Language Models Understand Mimed Actions?cited by 2
  18. 2025Watch, Listen, Understand, Mislead: Tri-modal Adversarial Attacks on Short Videos for Content Appropriateness Evaluationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026UniFinEval: Towards Unified Evaluation of Financial Multimodal Models across Text, Images and Videoscited by 0
  2. 2026IPO-Mine: A Toolkit and Dataset for Section-Structured Analysis of Long, Multimodal IPO Documentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Unlocking Financial Insights: An advanced Multimodal Summarization with Multimodal Output Framework for Financial Advisory Videos
  2. 2026Benchmarking Large Vision-Language Models on CFMME: A Comprehensive Chinese Financial Multimodal Evaluation Dataset
  3. 2026Paying for Too Many Tokens? Valid and Cost-Efficient Multimodal LLM Annotation with Simple Heuristics
  4. 2025Toward Scalable Video Narration: A Training-free Approach Using Multimodal Large Language Models
  5. 2025FinMR: A Knowledge-Intensive Multimodal Benchmark for Advanced Financial Reasoning
  6. 2024Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications
  7. 2025Evaluating Multimodal Large Language Models on Video Captioning via Monte Carlo Tree Search
  8. 2026MM-FinEval: A Multi-Task Multimodal Benchmark for Real-World Financial Forecasting