# OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition

arXiv: https://arxiv.org/abs/2312.00096 · HTML: https://mlsanity.com/paper/2312.00096/

## Key facts

- Cited by 16 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 53 of its 71 references that are in the map.
- First posted on arXiv 30 Nov 2023.

## 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 53)

- [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)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (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)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [Florence: A New Foundation Model for Computer Vision](https://mlsanity.com/paper/2111.11432/) (2021)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models](https://mlsanity.com/paper/2309.01219/) (2023)
- [InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation](https://mlsanity.com/paper/2307.06942/) (2023)
- [Visual Classification via Description from Large Language Models](https://mlsanity.com/paper/2210.07183/) (2022)
- [A Short Note about Kinetics-600](https://mlsanity.com/paper/1808.01340/) (2018)
- [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)
- [Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2309.15818/) (2023)
- [Joint Distribution Optimal Transportation for Domain Adaptation](https://mlsanity.com/paper/1705.08848/) (2017)
- [What does a platypus look like? Generating customized prompts for zero-shot image classification](https://mlsanity.com/paper/2209.03320/) (2022)
- [DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1803.10081/) (2018)
- [Patching open-vocabulary models by interpolating weights](https://mlsanity.com/paper/2208.05592/) (2022)
- [Frozen CLIP Models are Efficient Video Learners](https://mlsanity.com/paper/2208.03550/) (2022)
- [Fine-tuned CLIP Models are Efficient Video Learners](https://mlsanity.com/paper/2212.03640/) (2022)
- [Learning a Deep Embedding Model for Zero-Shot Learning](https://mlsanity.com/paper/1611.05088/) (2016)

## Built on by (most cited first, 16 of 16)

- [AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation](https://mlsanity.com/paper/2407.04603/) (2024)
- [Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms](https://mlsanity.com/paper/2408.09764/) (2024)
- [Leveraging Temporal Contextualization for Video Action Recognition](https://mlsanity.com/paper/2404.09490/) (2024)
- [Building a Multi-modal Spatiotemporal Expert for Zero-shot Action Recognition with CLIP](https://mlsanity.com/paper/2412.09895/) (2024)
- [Learning to Generalize without Bias for Open-Vocabulary Action Recognition](https://mlsanity.com/paper/2502.20158/) (2025)
- [Storyboard guided Alignment for Fine-grained Video Action Recognition](https://mlsanity.com/paper/2410.14238/) (2024)
- [Efficient Transfer Learning for Video-language Foundation Models](https://mlsanity.com/paper/2411.11223/) (2024)
- [VTD-CLIP: Video-to-Text Discretization via Prompting CLIP](https://mlsanity.com/paper/2503.18407/) (2025)
- [The Role of Video Generation in Enhancing Data-Limited Action Understanding](https://mlsanity.com/paper/2505.19495/) (2025)
- [ATSTrack: Enhancing Visual-Language Tracking by Aligning Temporal and Spatial Scales](https://mlsanity.com/paper/2507.00454/) (2025)
- [SPKLIP: Aligning Spike Video Streams with Natural Language](https://mlsanity.com/paper/2505.12656/) (2025)
- [GA2-CLIP: Generic Attribute Anchor for Efficient Prompt Tuningin Video-Language Models](https://mlsanity.com/paper/2511.22125/) (2025)
- [EV-CLIP: Efficient Visual Prompt Adaptation for CLIP in Few-shot Action Recognition under Visual Challenges](https://mlsanity.com/paper/2604.22595/) (2026)
- [Spatio-Temporal Similarity Volume Aggregation for Open-Vocabulary Action Recognition](https://mlsanity.com/paper/2605.23288/) (2026)
- [VidPrism: Heterogeneous Mixture of Experts for Image-to-Video Transfer](https://mlsanity.com/paper/2605.28229/) (2026)
- [TACO: Towards Task-Consistent Open-Vocabulary Adaptation in Video Recognition](https://mlsanity.com/paper/2606.25478/) (2026)

## Abstract (arXiv)

Due to the resource-intensive nature of training vision-language models on expansive video data, a majority of studies have centered on adapting pre-trained image-language models to the video domain. Dominant pipelines propose to tackle the visual discrepancies with additional temporal learners while overlooking the substantial discrepancy for web-scaled descriptive narratives and concise action category names, leading to less distinct semantic space and potential performance limitations. In this work, we prioritize the refinement of text knowledge to facilitate generalizable video recognition. To address the limitations of the less distinct semantic space of category names, we prompt a large language model (LLM) to augment action class names into Spatio-Temporal Descriptors thus bridging the textual discrepancy and serving as a knowledge base for general recognition. Moreover, to assign the best descriptors with different video instances, we propose Optimal Descriptor Solver, forming the video recognition problem as solving the optimal matching flow across frame-level representations and descriptors. Comprehensive evaluations in zero-shot, few-shot, and fully supervised video recognition highlight the effectiveness of our approach. Our best model achieves a state-of-the-art zero-shot accuracy of 75.1% on Kinetics-600.