# Beyond Raw Videos: Understanding Edited Videos with Large Multimodal Model

arXiv: https://arxiv.org/abs/2406.10484 · HTML: https://mlsanity.com/paper/2406.10484/

## Key facts

- Cited by 10 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 24 of its 37 references that are in the map.
- First posted on arXiv 15 Jun 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [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)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering](https://mlsanity.com/paper/1906.02467/) (2019)
- [LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models](https://mlsanity.com/paper/2311.17043/) (2023)
- [Masked Autoencoders As Spatiotemporal Learners](https://mlsanity.com/paper/2205.09113/) (2022)
- [Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers](https://mlsanity.com/paper/2402.19479/) (2024)
- [LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment](https://mlsanity.com/paper/2310.01852/) (2023)
- [PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning](https://mlsanity.com/paper/2404.16994/) (2024)
- [Video Understanding with Large Language Models: A Survey](https://mlsanity.com/paper/2312.17432/) (2023)
- [Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition](https://mlsanity.com/paper/1708.07632/) (2017)
- [VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples](https://mlsanity.com/paper/2103.05905/) (2021)
- [Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward](https://mlsanity.com/paper/2404.01258/) (2024)
- [AutoTransition: Learning to Recommend Video Transition Effects](https://mlsanity.com/paper/2207.13479/) (2022)
- [Edit3K: Universal Representation Learning for Video Editing Components](https://mlsanity.com/paper/2403.16048/) (2024)

## Built on by (most cited first, 10 of 10)

- [Survey of Adversarial Robustness in Multimodal Large Language Models](https://mlsanity.com/paper/2503.13962/) (2025)
- [VEU-Bench: Towards Comprehensive Understanding of Video Editing](https://mlsanity.com/paper/2504.17828/) (2025)
- [VF-Eval: Evaluating Multimodal LLMs for Generating Feedback on AIGC Videos](https://mlsanity.com/paper/2505.23693/) (2025)
- [AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding](https://mlsanity.com/paper/2512.16250/) (2025)
- [VEBench:Benchmarking Large Multimodal Models for Real-World Video Editing](https://mlsanity.com/paper/2605.03276/) (2026)
- [Deeply Dual Supervised learning for melanoma recognition](https://mlsanity.com/paper/2508.01994/) (2025)
- [Edge Detection for Organ Boundaries via Top Down Refinement and SubPixel Upsampling](https://mlsanity.com/paper/2508.06805/) (2025)
- [DualResolution Residual Architecture with Artifact Suppression for Melanocytic Lesion Segmentation](https://mlsanity.com/paper/2508.06816/) (2025)
- [VesselRW: Weakly Supervised Subcutaneous Vessel Segmentation via Learned Random Walk Propagation](https://mlsanity.com/paper/2508.06819/) (2025)
- [Kaleido: Algorithm-Hardware Co-Design for Video Diffusion Transformers by Exploiting Latent Space Correlations](https://mlsanity.com/paper/2607.13770/) (2026)

## Abstract (arXiv)

The emerging video LMMs (Large Multimodal Models) have achieved significant improvements on generic video understanding in the form of VQA (Visual Question Answering), where the raw videos are captured by cameras. However, a large portion of videos in real-world applications are edited videos, textite.g., users usually cut and add effects/modifications to the raw video before publishing it on social media platforms. The edited videos usually have high view counts but they are not covered in existing benchmarks of video LMMs, textiti.e., ActivityNet-QA, or VideoChatGPT benchmark. In this paper, we leverage the edited videos on a popular short video platform, textiti.e., TikTok, and build a video VQA benchmark (named EditVid-QA) covering four typical editing categories, i.e., effect, funny, meme, and game. Funny and meme videos benchmark nuanced understanding and high-level reasoning, while effect and game evaluate the understanding capability of artificial design. Most of the open-source video LMMs perform poorly on the EditVid-QA benchmark, indicating a huge domain gap between edited short videos on social media and regular raw videos. To improve the generalization ability of LMMs, we collect a training set for the proposed benchmark based on both Panda-70M/WebVid raw videos and small-scale TikTok/CapCut edited videos, which boosts the performance on the proposed EditVid-QA benchmark, indicating the effectiveness of high-quality training data. We also identified a serious issue in the existing evaluation protocol using the GPT-3.5 judge, namely a "sorry" attack, where a sorry-style naive answer can achieve an extremely high rating from the GPT judge, e.g., over 4.3 for correctness score on VideoChatGPT evaluation protocol. To avoid the "sorry" attacks, we evaluate results with GPT-4 judge and keyword filtering. The dataset is released at https://github.com/XenonLamb/EditVid-QA.