# FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding

arXiv: https://arxiv.org/abs/2503.14935 · HTML: https://mlsanity.com/paper/2503.14935/

## Key facts

- Cited by 24 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 50 of its 61 references that are in the map.
- First posted on arXiv 19 Mar 2025.

## 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 50)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs](https://mlsanity.com/paper/2406.07476/) (2024)
- [NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions](https://mlsanity.com/paper/2105.08276/) (2021)
- [Aligning Large Multimodal Models with Factually Augmented RLHF](https://mlsanity.com/paper/2309.14525/) (2023)
- [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023)
- [ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering](https://mlsanity.com/paper/1906.02467/) (2019)
- [MovieChat: From Dense Token to Sparse Memory for Long Video Understanding](https://mlsanity.com/paper/2307.16449/) (2023)
- [Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding](https://mlsanity.com/paper/1604.01753/) (2016)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers](https://mlsanity.com/paper/2402.19479/) (2024)
- [TempCompass: Do Video LLMs Really Understand Videos?](https://mlsanity.com/paper/2403.00476/) (2024)
- [OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation](https://mlsanity.com/paper/2407.02371/) (2024)
- [AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation](https://mlsanity.com/paper/2311.07397/) (2023)
- [MimicPlay: Long-Horizon Imitation Learning by Watching Human Play](https://mlsanity.com/paper/2302.12422/) (2023)
- [VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling](https://mlsanity.com/paper/2501.00574/) (2024)
- [Moments in Time Dataset: one million videos for event understanding](https://mlsanity.com/paper/1801.03150/) (2018)
- [STAR: A Benchmark for Situated Reasoning in Real-World Videos](https://mlsanity.com/paper/2405.09711/) (2024)

## Built on by (most cited first, 24 of 24)

- [MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe](https://mlsanity.com/paper/2509.18154/) (2025)
- [Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models](https://mlsanity.com/paper/2505.04921/) (2025)
- [MotionSight: Boosting Fine-Grained Motion Understanding in Multimodal LLMs](https://mlsanity.com/paper/2506.01674/) (2025)
- [MA-Bench: Towards Fine-grained Micro-Action Understanding](https://mlsanity.com/paper/2603.26586/) (2026)
- [ViStoryBench: Comprehensive Benchmark Suite for Story Visualization](https://mlsanity.com/paper/2505.24862/) (2025)
- [VideoPerceiver: Enhancing Fine-Grained Temporal Perception in Video Multimodal Large Language Models](https://mlsanity.com/paper/2511.18823/) (2025)
- [FoundationMotion: Auto-Labeling and Reasoning about Spatial Movement in Videos](https://mlsanity.com/paper/2512.10927/) (2025)
- [CurveStream: Boosting Streaming Video Understanding in MLLMs via Curvature-Aware Hierarchical Visual Memory Management](https://mlsanity.com/paper/2603.19571/) (2026)
- [Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events](https://mlsanity.com/paper/2606.02522/) (2026)
- [Revisiting Multimodal KV Cache Compression: A Frequency-Domain-Guided Outlier-KV-Aware Approach](https://mlsanity.com/paper/2511.16786/) (2025)
- [KPM-Bench: A Kinematic Parsing Motion Benchmark for Fine-grained Motion-centric Video Understanding](https://mlsanity.com/paper/2602.17768/) (2026)
- [Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video-LLMs](https://mlsanity.com/paper/2605.22823/) (2026)
- [OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering](https://mlsanity.com/paper/2604.08209/) (2026)
- [Exploring High-Order Self-Similarity for Video Understanding](https://mlsanity.com/paper/2604.20760/) (2026)
- [MotionAtlas: Detailed Region Captioning for Motion-Centric Videos](https://mlsanity.com/paper/2606.29531/) (2026)
- [Natural Language Camera Movement Understanding](https://mlsanity.com/paper/2607.03043/) (2026)
- [Beyond Description: Cognitively Benchmarking Fine-Grained Action for Embodied Agents](https://mlsanity.com/paper/2511.18685/) (2025)
- [Leum-VL Technical Report](https://mlsanity.com/paper/2603.20354/) (2026)
- [Can Multimodal Large Language Models Truly Understand Small Objects?](https://mlsanity.com/paper/2604.22884/) (2026)
- [BARISTA: A Multi-Task Egocentric Benchmark for Compositional Visual Understanding](https://mlsanity.com/paper/2605.12074/) (2026)
- [NextMotionQA: Benchmarking and Judging Human Motion Understanding with Vision-Language Models](https://mlsanity.com/paper/2606.04773/) (2026)
- [MotionEnhancer: Leveraging Video Diffusion for Motion-Enhanced Vision-Language Models](https://mlsanity.com/paper/2606.06853/) (2026)
- [TempCloze: Can Video-LLMs Identify the Missing Middle?](https://mlsanity.com/paper/2609.01515/) (2026)
- [Beyond Binary Preferences: Graded Preference Optimization for Limb-Motion Captioning](https://mlsanity.com/paper/2609.36628/) (2026)

## Abstract (arXiv)

Multimodal Large Language Models (MLLMs) have shown remarkable capabilities in video content understanding but still struggle with fine-grained motion comprehension. To comprehensively assess the motion understanding ability of existing MLLMs, we introduce FAVOR-Bench, comprising 1,776 videos with structured manual annotations of various motions. Our benchmark includes both close-ended and open-ended tasks. For close-ended evaluation, we carefully design 8,184 multiple-choice question-answer pairs spanning six distinct sub-tasks. For open-ended evaluation, we develop both a novel cost-efficient LLM-free and a GPT-assisted caption assessment method, where the former can enhance benchmarking interpretability and reproducibility. Comprehensive experiments with 21 state-of-the-art MLLMs reveal significant limitations in their ability to comprehend and describe detailed temporal dynamics in video motions. To alleviate this limitation, we further build FAVOR-Train, a dataset consisting of 17,152 videos with fine-grained motion annotations. The results of finetuning Qwen2.5-VL on FAVOR-Train yield consistent improvements on motion-related tasks of TVBench, MotionBench and our FAVOR-Bench. Comprehensive assessment results demonstrate that the proposed FAVOR-Bench and FAVOR-Train provide valuable tools to the community for developing more powerful video understanding models. Project page: hrefhttps://favor-bench.github.io/https://favor-bench.github.io/.