# Pretrained Image-Text Models are Secretly Video Captioners

arXiv: https://arxiv.org/abs/2502.13363 · HTML: https://mlsanity.com/paper/2502.13363/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 51 references that are in the map.
- First posted on arXiv 19 Feb 2025.

## Builds on (most cited first, 30 of 34)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022)
- [SimVLM: Simple Visual Language Model Pretraining with Weak Supervision](https://mlsanity.com/paper/2108.10904/) (2021)
- [VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding](https://mlsanity.com/paper/2109.14084/) (2021)
- [Self-critical Sequence Training for Image Captioning](https://mlsanity.com/paper/1612.00563/) (2016)
- [GIT: A Generative Image-to-text Transformer for Vision and Language](https://mlsanity.com/paper/2205.14100/) (2022)
- [VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research](https://mlsanity.com/paper/1904.03493/) (2019)
- [MERLOT: Multimodal Neural Script Knowledge Models](https://mlsanity.com/paper/2106.02636/) (2021)
- [Valley: Video Assistant with Large Language model Enhanced abilitY](https://mlsanity.com/paper/2306.07207/) (2023)
- [VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset](https://mlsanity.com/paper/2305.18500/) (2023)
- [mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video](https://mlsanity.com/paper/2302.00402/) (2023)
- [Align and Prompt: Video-and-Language Pre-training with Entity Prompts](https://mlsanity.com/paper/2112.09583/) (2021)
- [TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment](https://mlsanity.com/paper/2108.09980/) (2021)
- [Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation](https://mlsanity.com/paper/2303.12112/) (2023)
- [An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling](https://mlsanity.com/paper/2209.01540/) (2022)
- [VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners](https://mlsanity.com/paper/2212.04979/) (2022)
- [InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning](https://mlsanity.com/paper/2409.12568/) (2024)
- [Bootstrapping Vision-Language Learning with Decoupled Language Pre-training](https://mlsanity.com/paper/2307.07063/) (2023)
- [Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding](https://mlsanity.com/paper/2502.06020/) (2025)
- [MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks](https://mlsanity.com/paper/2303.16839/) (2023)
- [CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP](https://mlsanity.com/paper/2410.23330/) (2024)

## Built on by (most cited first, 11 of 11)

- [Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Models](https://mlsanity.com/paper/2502.15910/) (2025)
- [HTMuon: Improving Muon via Heavy-Tailed Spectral Correction](https://mlsanity.com/paper/2603.10067/) (2026)
- [Behavior Knowledge Merge in Reinforced Agentic Models](https://mlsanity.com/paper/2601.13572/) (2026)
- [Steering Multimodal Large Language Models Decoding for Context-Aware Safety](https://mlsanity.com/paper/2509.19212/) (2025)
- [Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner](https://mlsanity.com/paper/2506.01301/) (2025)
- [Music Audio-Visual Question Answering Requires Specialized Multimodal Designs](https://mlsanity.com/paper/2505.20638/) (2025)
- [Learning Sparsity for Effective and Efficient Music Performance Question Answering](https://mlsanity.com/paper/2506.01319/) (2025)
- [Growing Through Experience: Scaling Episodic Grounding in Language Models](https://mlsanity.com/paper/2506.01312/) (2025)
- [What Makes LLMs Effective Sequential Recommenders? A Study on Preference Intensity and Temporal Context](https://mlsanity.com/paper/2506.02261/) (2025)
- [ProtoVQA: An Adaptable Prototypical Framework for Explainable Fine-Grained Visual Question Answering](https://mlsanity.com/paper/2509.16680/) (2025)
- [Unified Vision-Language Modeling via Concept Space Alignment](https://mlsanity.com/paper/2603.01096/) (2026)

## Abstract (arXiv)

Developing video captioning models is computationally expensive. The dynamic nature of video also complicates the design of multimodal models that can effectively caption these sequences. However, we find that by using minimal computational resources and without complex modifications to address video dynamics, an image-based model can be repurposed to outperform several specialised video captioning systems. Our adapted model demonstrates top tier performance on major benchmarks, ranking 2nd on MSRVTT and MSVD, and 3rd on VATEX. We transform it into a competitive video captioner by post training a typical image captioning model BLIP2 with only 6,000 video text pairs and simply concatenating frames (significantly fewer data than other methods), which use 2.5 to 144 million pairs. From a resource optimization perspective, this video captioning study focuses on three fundamental factors: optimizing model scale, maximizing data efficiency, and incorporating reinforcement learning. This extensive study demonstrates that a lightweight, image based adaptation strategy can rival state-of-the-art video captioning systems, offering a practical solution for low-resource scenarios.