# Knowledge is Power: Advancing Few-shot Action Recognition with Multimodal Semantics from MLLMs

arXiv: https://arxiv.org/abs/2603.26033 · HTML: https://mlsanity.com/paper/2603.26033/

## Key facts

- No citing papers in the map yet (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 51 references that are in the map.
- First posted on arXiv 27 Mar 2026.

## 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)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [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)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [AIM: Adapting Image Models for Efficient Video Action Recognition](https://mlsanity.com/paper/2302.03024/) (2023)
- [Few-Shot Video Classification via Temporal Alignment](https://mlsanity.com/paper/1906.11415/) (2019)
- [Contextual Object Detection with Multimodal Large Language Models](https://mlsanity.com/paper/2305.18279/) (2023)
- [One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos](https://mlsanity.com/paper/2409.19603/) (2024)
- [Temporal-Relational CrossTransformers for Few-Shot Action Recognition](https://mlsanity.com/paper/2101.06184/) (2021)
- [Spatio-temporal Relation Modeling for Few-shot Action Recognition](https://mlsanity.com/paper/2112.05132/) (2021)
- [LLM-Seg: Bridging Image Segmentation and Large Language Model Reasoning](https://mlsanity.com/paper/2404.08767/) (2024)
- [Hybrid Relation Guided Set Matching for Few-shot Action Recognition](https://mlsanity.com/paper/2204.13423/) (2022)
- [CLIP-guided Prototype Modulating for Few-shot Action Recognition](https://mlsanity.com/paper/2303.02982/) (2023)
- [MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition](https://mlsanity.com/paper/2304.00946/) (2023)
- [MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognition](https://mlsanity.com/paper/2405.02077/) (2024)

## Abstract (arXiv)

Multimodal Large Language Models (MLLMs) have propelled the field of few-shot action recognition (FSAR). However, preliminary explorations in this area primarily focus on generating captions to form a suboptimal feature->caption->feature pipeline and adopt metric learning solely within the visual space. In this paper, we propose FSAR-LLaVA, the first end-to-end method to leverage MLLMs (such as Video-LLaVA) as a multimodal knowledge base for directly enhancing FSAR. First, at the feature level, we leverage the MLLM's multimodal decoder to extract spatiotemporally and semantically enriched representations, which are then decoupled and enhanced by our Multimodal Feature-Enhanced Module into distinct visual and textual features that fully exploit their semantic knowledge for FSAR. Next, we leverage the versatility of MLLMs to craft input prompts that flexibly adapt to diverse scenarios, and use their aligned outputs to drive our designed Composite Task-Oriented Prototype Construction, effectively bridging the distribution gap between meta-train and meta-test sets. Finally, to enable multimodal features to guide metric learning jointly, we introduce a training-free Multimodal Prototype Matching Metric that adaptively selects the most decisive cues and efficiently leverages the decoupled feature representations produced by MLLMs. Extensive experiments demonstrate superior performance across various tasks with minimal trainable parameters.