# Learning video embedding space with Natural Language Supervision

arXiv: https://arxiv.org/abs/2303.14584 · HTML: https://mlsanity.com/paper/2303.14584/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 19 references that are in the map.
- First posted on arXiv 25 Mar 2023.

## Builds on (most cited first, 13 of 13)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling](https://mlsanity.com/paper/2102.06183/) (2021)
- [A Short Note on the Kinetics-700-2020 Human Action Dataset](https://mlsanity.com/paper/2010.10864/) (2020)
- [Interpretable Adversarial Perturbation in Input Embedding Space for Text](https://mlsanity.com/paper/1805.02917/) (2018)
- [AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation](https://mlsanity.com/paper/1803.01599/) (2018)
- [Ask, Acquire, and Attack: Data-free UAP Generation using Class Impressions](https://mlsanity.com/paper/1808.01153/) (2018)
- [Exploring the Space of Adversarial Images](https://mlsanity.com/paper/1510.05328/) (2015)
- [Unsupervised Feature Learning of Human Actions as Trajectories in Pose Embedding Manifold](https://mlsanity.com/paper/1812.02592/) (2018)
- [Dynamic Object Removal for Effective Slam](https://mlsanity.com/paper/2303.10923/) (2023)

## Built on by (most cited first, 1 of 1)

- [TransDocs: Optical Character Recognition with word to word translation](https://mlsanity.com/paper/2304.07637/) (2023)

## Abstract (arXiv)

The recent success of the CLIP model has shown its potential to be applied to a wide range of vision and language tasks. However this only establishes embedding space relationship of language to images, not to the video domain. In this paper, we propose a novel approach to map video embedding space to natural langugage. We propose a two-stage approach that first extracts visual features from each frame of a video using a pre-trained CNN, and then uses the CLIP model to encode the visual features for the video domain, along with the corresponding text descriptions. We evaluate our method on two benchmark datasets, UCF101 and HMDB51, and achieve state-of-the-art performance on both tasks.