# Q-Adapter: Visual Query Adapter for Extracting Textually-related Features in Video Captioning

arXiv: https://arxiv.org/abs/2510.10022 · HTML: https://mlsanity.com/paper/2510.10022/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 44 references that are in the map.
- First posted on arXiv 11 Oct 2025.

## Builds on (most cited first, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks](https://mlsanity.com/paper/2112.06825/) (2021)
- [Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning](https://mlsanity.com/paper/2302.14115/) (2023)
- [VTimeLLM: Empower LLM to Grasp Video Moments](https://mlsanity.com/paper/2311.18445/) (2023)
- [AdapterDrop: On the Efficiency of Adapters in Transformers](https://mlsanity.com/paper/2010.11918/) (2020)
- [A Dataset for Movie Description](https://mlsanity.com/paper/1501.02530/) (2015)
- [VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset](https://mlsanity.com/paper/2305.18500/) (2023)
- [End-to-end Generative Pretraining for Multimodal Video Captioning](https://mlsanity.com/paper/2201.08264/) (2022)
- [CLIP4Caption: CLIP for Video Caption](https://mlsanity.com/paper/2110.06615/) (2021)
- [Jointly Modeling Embedding and Translation to Bridge Video and Language](https://mlsanity.com/paper/1505.01861/) (2015)
- [Open-book Video Captioning with Retrieve-Copy-Generate Network](https://mlsanity.com/paper/2103.05284/) (2021)
- [Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval](https://mlsanity.com/paper/2404.07610/) (2024)
- [5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks](https://mlsanity.com/paper/2408.08345/) (2024)
- [Time-, Memory- and Parameter-Efficient Visual Adaptation](https://mlsanity.com/paper/2402.02887/) (2024)
- [Eliciting In-Context Learning in Vision-Language Models for Videos Through Curated Data Distributional Properties](https://mlsanity.com/paper/2311.17041/) (2023)

## Built on by (most cited first, 3 of 3)

- [Image-to-Video Transfer Learning based on Image-Language Foundation Models: A Comprehensive Survey](https://mlsanity.com/paper/2510.10671/) (2025)
- [ReDiPrune: Relevance-Diversity Pre-Projection Token Pruning for Efficient Multimodal LLMs](https://mlsanity.com/paper/2603.24680/) (2026)
- [TraRA: Trajectory-level Recognition Aggregation for Video Text Spotting in Urban Surveillance](https://mlsanity.com/paper/2606.07161/) (2026)

## Abstract (arXiv)

Recent advances in video captioning are driven by large-scale pretrained models, which follow the standard "pre-training followed by fine-tuning" paradigm, where the full model is fine-tuned for downstream tasks. Although effective, this approach becomes computationally prohibitive as the model size increases. The Parameter-Efficient Fine-Tuning (PEFT) approach offers a promising alternative, but primarily focuses on the language components of Multimodal Large Language Models (MLLMs). Despite recent progress, PEFT remains underexplored in multimodal tasks and lacks sufficient understanding of visual information during fine-tuning the model. To bridge this gap, we propose Query-Adapter (Q-Adapter), a lightweight visual adapter module designed to enhance MLLMs by enabling efficient fine-tuning for the video captioning task. Q-Adapter introduces learnable query tokens and a gating layer into Vision Encoder, enabling effective extraction of sparse, caption-relevant features without relying on external textual supervision. We evaluate Q-Adapter on two well-known video captioning datasets, MSR-VTT and MSVD, where it achieves state-of-the-art performance among the methods that take the PEFT approach across BLEU@4, METEOR, ROUGE-L, and CIDEr metrics. Q-Adapter also achieves competitive performance compared to methods that take the full fine-tuning approach while requiring only 1.4% of the parameters. We further analyze the impact of key hyperparameters and design choices on fine-tuning effectiveness, providing insights into optimization strategies for adapter-based learning. These results highlight the strong potential of Q-Adapter in balancing caption quality and parameter efficiency, demonstrating its scalability for video-language modeling.