# Semantic-aware Video Representation for Few-shot Action Recognition

arXiv: https://arxiv.org/abs/2311.06218 · HTML: https://mlsanity.com/paper/2311.06218/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 62 references that are in the map.
- First posted on arXiv 10 Nov 2023.

## Builds on (most cited first, 30 of 45)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [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)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Scaling Egocentric Vision: The EPIC-KITCHENS Dataset](https://mlsanity.com/paper/1804.02748/) (2018)
- [Learning to learn by gradient descent by gradient descent](https://mlsanity.com/paper/1606.04474/) (2016)
- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [How to train your MAML](https://mlsanity.com/paper/1810.09502/) (2018)
- [A Baseline for Few-Shot Image Classification](https://mlsanity.com/paper/1909.02729/) (2019)
- [Frustratingly Simple Few-Shot Object Detection](https://mlsanity.com/paper/2003.06957/) (2020)
- [Cross Attention Network for Few-shot Classification](https://mlsanity.com/paper/1910.07677/) (2019)
- [Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition](https://mlsanity.com/paper/1708.07632/) (2017)
- [CrossTransformers: spatially-aware few-shot transfer](https://mlsanity.com/paper/2007.11498/) (2020)
- [VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset](https://mlsanity.com/paper/2304.08345/) (2023)
- [Few-Shot Video Classification via Temporal Alignment](https://mlsanity.com/paper/1906.11415/) (2019)
- [Finding Task-Relevant Features for Few-Shot Learning by Category Traversal](https://mlsanity.com/paper/1905.11116/) (2019)
- [Learning to Compose Domain-Specific Transformations for Data Augmentation](https://mlsanity.com/paper/1709.01643/) (2017)
- [Temporal-Relational CrossTransformers for Few-Shot Action Recognition](https://mlsanity.com/paper/2101.06184/) (2021)

## Built on by (most cited first, 7 of 7)

- [A Comprehensive Review of Few-shot Action Recognition](https://mlsanity.com/paper/2407.14744/) (2024)
- [Trokens: Semantic-Aware Relational Trajectory Tokens for Few-Shot Action Recognition](https://mlsanity.com/paper/2508.03695/) (2025)
- [Beyond Label Semantics: Language-Guided Action Anatomy for Few-shot Action Recognition](https://mlsanity.com/paper/2507.16287/) (2025)
- [Hierarchical Relation-augmented Representation Generalization for Few-shot Action Recognition](https://mlsanity.com/paper/2504.10079/) (2025)
- [A2M2-Net: Adaptively Aligned Multi-Scale Moment for Few-Shot Action Recognition](https://mlsanity.com/paper/2509.17638/) (2025)
- [Efficient Generalization via Multimodal Co-Training under Data Scarcity and Distribution Shift](https://mlsanity.com/paper/2510.07509/) (2025)
- [A Baseline Study and Benchmark for Few-Shot Open-Set Action Recognition with Feature Residual Discrimination](https://mlsanity.com/paper/2603.04125/) (2026)

## Abstract (arXiv)

Recent work on action recognition leverages 3D features and textual information to achieve state-of-the-art performance. However, most of the current few-shot action recognition methods still rely on 2D frame-level representations, often require additional components to model temporal relations, and employ complex distance functions to achieve accurate alignment of these representations. In addition, existing methods struggle to effectively integrate textual semantics, some resorting to concatenation or addition of textual and visual features, and some using text merely as an additional supervision without truly achieving feature fusion and information transfer from different modalities. In this work, we propose a simple yet effective Semantic-Aware Few-Shot Action Recognition (SAFSAR) model to address these issues. We show that directly leveraging a 3D feature extractor combined with an effective feature-fusion scheme, and a simple cosine similarity for classification can yield better performance without the need of extra components for temporal modeling or complex distance functions. We introduce an innovative scheme to encode the textual semantics into the video representation which adaptively fuses features from text and video, and encourages the visual encoder to extract more semantically consistent features. In this scheme, SAFSAR achieves alignment and fusion in a compact way. Experiments on five challenging few-shot action recognition benchmarks under various settings demonstrate that the proposed SAFSAR model significantly improves the state-of-the-art performance.