# Watching Synthetic Videos: Aligning Cross-modal Representations with Visual Synthesis for Zero-shot Video Captioning

arXiv: https://arxiv.org/abs/2608.11013 · HTML: https://mlsanity.com/paper/2608.11013/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 41 references that are in the map.
- First posted on arXiv 11 Aug 2026.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research](https://mlsanity.com/paper/1904.03493/) (2019)
- [Expanding Language-Image Pretrained Models for General Video Recognition](https://mlsanity.com/paper/2208.02816/) (2022)
- [MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding](https://mlsanity.com/paper/2404.05726/) (2024)
- [SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning](https://mlsanity.com/paper/2111.13196/) (2021)
- [Sequence to Sequence -- Video to Text](https://mlsanity.com/paper/1505.00487/) (2015)
- [ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic](https://mlsanity.com/paper/2111.14447/) (2021)
- [AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark](https://mlsanity.com/paper/2410.03051/) (2024)
- [Text-Only Training for Image Captioning using Noise-Injected CLIP](https://mlsanity.com/paper/2211.00575/) (2022)
- [Language Models Can See: Plugging Visual Controls in Text Generation](https://mlsanity.com/paper/2205.02655/) (2022)
- [Describing Videos by Exploiting Temporal Structure](https://mlsanity.com/paper/1502.08029/) (2015)
- [DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training](https://mlsanity.com/paper/2303.03032/) (2023)
- [Hierarchical Modular Network for Video Captioning](https://mlsanity.com/paper/2111.12476/) (2021)
- [Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data](https://mlsanity.com/paper/2401.08567/) (2024)
- [Zero-Shot Video Captioning with Evolving Pseudo-Tokens](https://mlsanity.com/paper/2207.11100/) (2022)
- [Improving Cross-modal Alignment with Synthetic Pairs for Text-only Image Captioning](https://mlsanity.com/paper/2312.08865/) (2023)
- [Delving Deeper into the Decoder for Video Captioning](https://mlsanity.com/paper/2001.05614/) (2020)
- [MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning](https://mlsanity.com/paper/2308.13218/) (2023)
- [From Association to Generation: Text-only Captioning by Unsupervised Cross-modal Mapping](https://mlsanity.com/paper/2304.13273/) (2023)
- [IFCap: Image-like Retrieval and Frequency-based Entity Filtering for Zero-shot Captioning](https://mlsanity.com/paper/2409.18046/) (2024)
- [Learning to Compose Topic-Aware Mixture of Experts for Zero-Shot Video Captioning](https://mlsanity.com/paper/1811.02765/) (2018)
- [RETTA: Retrieval-Enhanced Test-Time Adaptation for Zero-Shot Video Captioning](https://mlsanity.com/paper/2405.07046/) (2024)
- [Bidirectional Long-Short Term Memory for Video Description](https://mlsanity.com/paper/1606.04631/) (2016)

## Abstract (arXiv)

Text-only training is a popular paradigm in zero-shot video captioning, where the video distribution is not available to the model during training, leading to a cross-modal gap between the training (text-only) and the inference (video-only). Previous works attempt to bridge the gap through simple linear transformations. However, the inherent gap between text and video makes cross-modal representation space alignment insufficient, resulting in inaccurate sentences. To address this issue, we propose a novel zero-shot video captioning framework (WSV) consisting of two training stages, which first generates corresponding synthetic video latent representations via a pretrained text-to-video generation model. To strengthen the fidelity of the latent representations, we propose a polisher capable of bridging the gap between real and synthetic video distributions. Subsequently, we design a prompter that conditions GPT-2 on the polished latent representations to generate the captions in the second training stage. During inference, an input video is encoded by a pretrained 3D Causal VAE and then fed directly into the prompter, which in turn guides GPT-2 to produce the final caption. Experimental results conducted on MSVD, MSR-VTT, and VATEX datasets demonstrate that our proposed method achieves scores of 52 and 95.7 on the B@4 and CIDEr metrics, respectively.