# EVE: Towards End-to-End Video Subtitle Extraction with Vision-Language Models

arXiv: https://arxiv.org/abs/2503.04058 · HTML: https://mlsanity.com/paper/2503.04058/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Video understanding with MLLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 31 of its 49 references that are in the map.
- First posted on arXiv 6 Mar 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)

## Builds on (most cited first, 30 of 31)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models](https://mlsanity.com/paper/2311.17043/) (2023)
- [MovieChat: From Dense Token to Sparse Memory for Long Video Understanding](https://mlsanity.com/paper/2307.16449/) (2023)
- [TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding](https://mlsanity.com/paper/2312.02051/) (2023)
- [Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations](https://mlsanity.com/paper/2202.07800/) (2022)
- [PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning](https://mlsanity.com/paper/2404.16994/) (2024)
- [VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos](https://mlsanity.com/paper/2405.19209/) (2024)
- [Long-Term Feature Banks for Detailed Video Understanding](https://mlsanity.com/paper/1812.05038/) (2018)
- [Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition](https://mlsanity.com/paper/1406.2227/) (2014)
- [Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution](https://mlsanity.com/paper/2409.12961/) (2024)
- [Towards Long-Form Video Understanding](https://mlsanity.com/paper/2106.11310/) (2021)
- [ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard](https://mlsanity.com/paper/1912.09641/) (2019)
- [LITA: Language Instructed Temporal-Localization Assistant](https://mlsanity.com/paper/2403.19046/) (2024)
- [An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM](https://mlsanity.com/paper/2403.18406/) (2024)
- [Detecting Text in Natural Image with Connectionist Text Proposal Network](https://mlsanity.com/paper/1609.03605/) (2016)
- [DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models](https://mlsanity.com/paper/2405.20985/) (2024)
- [Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models](https://mlsanity.com/paper/2301.00182/) (2022)
- [Elysium: Exploring Object-level Perception in Videos via MLLM](https://mlsanity.com/paper/2403.16558/) (2024)
- [SubER: A Metric for Automatic Evaluation of Subtitle Quality](https://mlsanity.com/paper/2205.05805/) (2022)

## Built on by (most cited first, 6 of 6)

- [Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark](https://mlsanity.com/paper/2504.14693/) (2025)
- [Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoning](https://mlsanity.com/paper/2505.15154/) (2025)
- [CME-CAD: Heterogeneous Collaborative Multi-Expert Reinforcement Learning for CAD Code Generation](https://mlsanity.com/paper/2512.23333/) (2025)
- [MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement](https://mlsanity.com/paper/2508.09670/) (2025)
- [CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2506.00568/) (2025)
- [Gather and Trace: Rethinking Video TextVQA from an Instance-oriented Perspective](https://mlsanity.com/paper/2508.04197/) (2025)

## Abstract (arXiv)

Video subtitles play a crucial role in short videos and movies, as they not only help models better understand video content but also support applications such as video translation and content retrieval. Existing video subtitle extraction methods typically rely on multi-stage frameworks, where errors accumulate across stages and temporal dependencies are underutilized due to frame-wise processing. Moreover, although some Large Vision-Language Models (LVLMs) possess strong OCR capabilities, predicting accurate timestamps for subtitle texts remains challenging. To this end, we propose an End-to-end Video subtitle Extraction framework based on LVLMs, named EVE, which can output subtitles and their timestamps simultaneously. Specifically, we introduce a dual-branch Spatiotemporal Subtitle-Salient (Stextsuperscript3) Module that serves as an adapter for LVLMs, capable of representing subtitle-related content and considering inter-frame correlations using only a small number of tokens. Within this module, the Spatial Semantic Context Aggregate branch aggregates high-level global semantics to provide spatial visual contextual information, while the Temporal Subtitle Token Query branch explicitly queries subtitle-relevant tokens while considering temporal correlation across frames. The small number of tokens retained by the Stextsuperscript3 module are fed to the language model, which then directly outputs the subtitle text along with its timestamps. Furthermore, we construct the first large-scale dataset dedicated to video subtitle extraction, ViSa, containing over 2.5M videos with timestamped and bilingual annotation, thereby providing the community with a well-organized training and evaluation benchmark.