# Vamos: Versatile Action Models for Video Understanding

arXiv: https://arxiv.org/abs/2311.13627 · HTML: https://mlsanity.com/paper/2311.13627/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Builds on 68 of its 91 references that are in the map.
- First posted on arXiv 22 Nov 2023.

## Builds on (most cited first, 30 of 68)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [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)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Scaling Egocentric Vision: The EPIC-KITCHENS Dataset](https://mlsanity.com/paper/1804.02748/) (2018)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions](https://mlsanity.com/paper/2105.08276/) (2021)
- [VideoBERT: A Joint Model for Video and Language Representation Learning](https://mlsanity.com/paper/1904.01766/) (2019)
- [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023)
- [VideoGPT: Video Generation using VQ-VAE and Transformers](https://mlsanity.com/paper/2104.10157/) (2021)
- [FLAVA: A Foundational Language And Vision Alignment Model](https://mlsanity.com/paper/2112.04482/) (2021)
- [ViperGPT: Visual Inference via Python Execution for Reasoning](https://mlsanity.com/paper/2303.08128/) (2023)
- [Visual Programming: Compositional visual reasoning without training](https://mlsanity.com/paper/2211.11559/) (2022)
- [Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language](https://mlsanity.com/paper/2204.00598/) (2022)
- [Large Language Models Are Zero-Shot Time Series Forecasters](https://mlsanity.com/paper/2310.07820/) (2023)

## Built on by (most cited first, 30 of 40)

- [VideoAgent: Long-form Video Understanding with Large Language Model as Agent](https://mlsanity.com/paper/2403.10517/) (2024)
- [Video Understanding with Large Language Models: A Survey](https://mlsanity.com/paper/2312.17432/) (2023)
- [Streaming Long Video Understanding with Large Language Models](https://mlsanity.com/paper/2405.16009/) (2024)
- [HourVideo: 1-Hour Video-Language Understanding](https://mlsanity.com/paper/2411.04998/) (2024)
- [Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA](https://mlsanity.com/paper/2406.09396/) (2024)
- [DrVideo: Document Retrieval Based Long Video Understanding](https://mlsanity.com/paper/2406.12846/) (2024)
- [Language Repository for Long Video Understanding](https://mlsanity.com/paper/2403.14622/) (2024)
- [LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos](https://mlsanity.com/paper/2312.05269/) (2023)
- [Memory Consolidation Enables Long-Context Video Understanding](https://mlsanity.com/paper/2402.05861/) (2024)
- [PALM: Predicting Actions through Language Models](https://mlsanity.com/paper/2311.17944/) (2023)
- [VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs](https://mlsanity.com/paper/2409.20365/) (2024)
- [Understanding Long Videos with Multimodal Language Models](https://mlsanity.com/paper/2403.16998/) (2024)
- [VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges](https://mlsanity.com/paper/2409.01071/) (2024)
- [SlowFocus: Enhancing Fine-grained Temporal Understanding in Video LLM](https://mlsanity.com/paper/2602.03589/) (2026)
- [TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment](https://mlsanity.com/paper/2405.13911/) (2024)
- [Unifying Specialized Visual Encoders for Video Language Models](https://mlsanity.com/paper/2501.01426/) (2025)
- [Long Video Understanding with Learnable Retrieval in Video-Language Models](https://mlsanity.com/paper/2312.04931/) (2023)
- [StimuVAR: Spatiotemporal Stimuli-aware Video Affective Reasoning with Multimodal Large Language Models](https://mlsanity.com/paper/2409.00304/) (2024)
- [How Can Objects Help Video-Language Understanding?](https://mlsanity.com/paper/2504.07454/) (2025)
- [Enhancing Concept Localization in CLIP-based Concept Bottleneck Models](https://mlsanity.com/paper/2510.07115/) (2025)
- [VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG](https://mlsanity.com/paper/2604.05418/) (2026)
- [ReasVQA: Advancing VideoQA with Imperfect Reasoning Process](https://mlsanity.com/paper/2501.13536/) (2025)
- [MASR: Self-Reflective Reasoning through Multimodal Hierarchical Attention Focusing for Agent-based Video Understanding](https://mlsanity.com/paper/2504.17213/) (2025)
- [ViQAgent: Zero-Shot Video Question Answering via Agent with Open-Vocabulary Grounding Validation](https://mlsanity.com/paper/2505.15928/) (2025)
- [Enhancing Visual Planning with Auxiliary Tasks and Multi-token Prediction](https://mlsanity.com/paper/2507.15130/) (2025)
- [FineQuest: Adaptive Knowledge-Assisted Sports Video Understanding via Agent-of-Thoughts Reasoning](https://mlsanity.com/paper/2509.11796/) (2025)
- [START: Spatial and Textual Learning for Chart Understanding](https://mlsanity.com/paper/2512.07186/) (2025)
- [VidCtx: Context-aware Video Question Answering with Image Models](https://mlsanity.com/paper/2412.17415/) (2024)
- [Spacewalk-18: A Benchmark for Multimodal and Long-form Procedural Video Understanding in Novel Domains](https://mlsanity.com/paper/2311.18773/) (2023)
- [KFFocus: Highlighting Keyframes for Enhanced Video Understanding](https://mlsanity.com/paper/2508.08989/) (2025)

## Abstract (arXiv)

What makes good representations for video understanding, such as anticipating future activities, or answering video-conditioned questions? While earlier approaches focus on end-to-end learning directly from video pixels, we propose to revisit text-based representations, such as general-purpose video captions, which are interpretable and can be directly consumed by large language models (LLMs). Intuitively, different video understanding tasks may require representations that are complementary and at different granularity. To this end, we propose versatile action models (Vamos), a learning framework powered by a large language model as the ``reasoner'', and can flexibly leverage visual embedding and free-form text descriptions as its input. To interpret the important text evidence for question answering, we generalize the concept bottleneck model to work with tokens and nonlinear models, which uses hard attention to select a small subset of tokens from the free-form text as inputs to the LLM reasoner. We evaluate Vamos on five complementary benchmarks, Ego4D, NeXT-QA, IntentQA, Spacewalk-18, and EgoSchema, on its capability to model temporal dynamics, encode visual history, and perform reasoning. Surprisingly, we observe that text-based representations consistently achieve competitive performance on all benchmarks, and that visual embeddings provide marginal or no performance improvement, demonstrating the effectiveness of text-based video representation in the LLM era. We also demonstrate that our token bottleneck model is able to select relevant evidence from free-form text, support test-time intervention, and achieves nearly 5 times inference speedup while keeping a competitive question answering performance. Code and models are publicly released at https://brown-palm.github.io/Vamos/