# Efficient Transfer Learning for Video-language Foundation Models

arXiv: https://arxiv.org/abs/2411.11223 · HTML: https://mlsanity.com/paper/2411.11223/

## Key facts

- Cited by 4 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 36 of its 45 references that are in the map.
- First posted on arXiv 18 Nov 2024.

## 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 36)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [Florence: A New Foundation Model for Computer Vision](https://mlsanity.com/paper/2111.11432/) (2021)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [MaPLe: Multi-modal Prompt Learning](https://mlsanity.com/paper/2210.03117/) (2022)
- [Image Segmentation Using Text and Image Prompts](https://mlsanity.com/paper/2112.10003/) (2021)
- [InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation](https://mlsanity.com/paper/2307.06942/) (2023)
- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification](https://mlsanity.com/paper/2207.09519/) (2022)
- [Expanding Language-Image Pretrained Models for General Video Recognition](https://mlsanity.com/paper/2208.02816/) (2022)
- [ActionCLIP: A New Paradigm for Video Action Recognition](https://mlsanity.com/paper/2109.08472/) (2021)
- [Prompting Visual-Language Models for Efficient Video Understanding](https://mlsanity.com/paper/2112.04478/) (2021)
- [ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning](https://mlsanity.com/paper/2206.13559/) (2022)
- [Fine-tuned CLIP Models are Efficient Video Learners](https://mlsanity.com/paper/2212.03640/) (2022)
- [AIM: Adapting Image Models for Efficient Video Action Recognition](https://mlsanity.com/paper/2302.03024/) (2023)
- [PromptDet: Towards Open-vocabulary Detection using Uncurated Images](https://mlsanity.com/paper/2203.16513/) (2022)
- [CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching](https://mlsanity.com/paper/2303.13076/) (2023)
- [Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting](https://mlsanity.com/paper/2304.03307/) (2023)
- [Elaborative Rehearsal for Zero-shot Action Recognition](https://mlsanity.com/paper/2108.02833/) (2021)

## Built on by (most cited first, 4 of 4)

- [Image-to-Video Transfer Learning based on Image-Language Foundation Models: A Comprehensive Survey](https://mlsanity.com/paper/2510.10671/) (2025)
- [Multiview Self-Representation Learning across Heterogeneous Views](https://mlsanity.com/paper/2602.04328/) (2026)
- [VidPrism: Heterogeneous Mixture of Experts for Image-to-Video Transfer](https://mlsanity.com/paper/2605.28229/) (2026)
- [TALON: Token-Aligned Lightweight Adapters for 6-DoF Spacecraft Pose Estimation](https://mlsanity.com/paper/2605.31217/) (2026)

## Abstract (arXiv)

Pre-trained vision-language models provide a robust foundation for efficient transfer learning across various downstream tasks. In the field of video action recognition, mainstream approaches often introduce additional modules to capture temporal information. Although the additional modules increase the capacity of model, enabling it to better capture video-specific inductive biases, existing methods typically introduce a substantial number of new parameters and are prone to catastrophic forgetting of previously acquired generalizable knowledge. In this paper, we propose a parameter-efficient Multi-modal Spatio-Temporal Adapter (MSTA) to enhance the alignment between textual and visual representations, achieving a balance between generalizable knowledge and task-specific adaptation. Furthermore, to mitigate over-fitting and enhance generalizability, we introduce a spatio-temporal description-guided consistency constraint.This constraint involves providing template inputs (e.g., "a video of cls") to the trainable language branch and LLM-generated spatio-temporal descriptions to the pre-trained language branch, enforcing output consistency between the branches. This approach reduces overfitting to downstream tasks and enhances the distinguishability of the trainable branch within the spatio-temporal semantic space. We evaluate the effectiveness of our approach across four tasks: zero-shot transfer, few-shot learning, base-to-novel generalization, and fully-supervised learning. Compared to many state-of-the-art methods, our MSTA achieves outstanding performance across all evaluations, while using only 2-7% of the trainable parameters in the original model.