Beyond Raw Videos: Understanding Edited Videos with Large Multimodal Model

• URL: http://arxiv.org/abs/2406.10484v2
• Date: Fri, 27 Sep 2024 02:47:55 GMT
• Title: Beyond Raw Videos: Understanding Edited Videos with Large Multimodal Model
• Authors: Lu Xu, Sijie Zhu, Chunyuan Li, Chia-Wen Kuo, Fan Chen, Xinyao Wang, Guang Chen, Dawei Du, Ye Yuan, Longyin Wen,
• Abstract summary: We build a video VQA benchmark covering editing categories, i.e., effect, funny, meme, and game. Most of the open-source video LMMs perform poorly on the 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.
• Score: 62.38322742493649
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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, \textit{e.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, \textit{i.e.}, ActivityNet-QA, or VideoChatGPT benchmark. In this paper, we leverage the edited videos on a popular short video platform, \textit{i.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.

Related papers

• E-Bench: Subjective-Aligned Benchmark Suite for Text-Driven Video Editing Quality Assessment [6.627422081288281]
  E-Bench is a benchmark suite tailored to the assessment of text-driven video editing. It includes E-Bench DB, a video quality assessment (VQA) database for video editing. E-Bench QA focuses on the text-video alignment and the relevance modeling between source and edited videos.
  arXiv  Detail & Related papers  (2024-08-21T09:49:32Z)
• Goldfish: Vision-Language Understanding of Arbitrarily Long Videos [51.547065479762715]
  We present a methodology tailored for comprehending videos of arbitrary lengths. We also introduce the TVQA-long benchmark, designed to evaluate models' capabilities in understanding long videos with questions in both vision and text content. Our results indicate that our models have significant improvements in both long and short-video understanding.
  arXiv  Detail & Related papers  (2024-07-17T15:59:32Z)
• VideoPrism: A Foundational Visual Encoder for Video Understanding [90.01845485201746]
  VideoPrism is a general-purpose video encoder that tackles diverse video understanding tasks with a single frozen model. We pretrain VideoPrism on a heterogeneous corpus containing 36M high-quality video-caption pairs and 582M video clips with noisy parallel text. We extensively test VideoPrism on four broad groups of video understanding tasks, from web video question answering to CV for science, achieving state-of-the-art performance on 31 out of 33 video understanding benchmarks.
  arXiv  Detail & Related papers  (2024-02-20T18:29:49Z)
• PG-Video-LLaVA: Pixel Grounding Large Video-Language Models [52.83065081926238]
  We propose PG-Video-LLaVA, the first LMM with pixel-level grounding capability, integrating audio cues by transcribing them into text to enrich video-context understanding. Our framework builds on SoTA image-based LLaVA model and extends its advantages to the video domain, delivering promising gains on video-based conversation and grounding tasks.
  arXiv  Detail & Related papers  (2023-11-22T14:48:30Z)
• Perception Test: A Diagnostic Benchmark for Multimodal Video Models [78.64546291816117]
  We propose a novel multimodal video benchmark to evaluate the perception and reasoning skills of pre-trained multimodal models. The Perception Test focuses on skills (Memory, Abstraction, Physics, Semantics) and types of reasoning (descriptive, explanatory, predictive, counterfactual) across video, audio, and text modalities. The benchmark probes pre-trained models for their transfer capabilities, in a zero-shot / few-shot or limited finetuning regime.
  arXiv  Detail & Related papers  (2023-05-23T07:54:37Z)
• Video Question Answering with Iterative Video-Text Co-Tokenization [77.66445727743508]
  We propose a novel multi-stream video encoder for video question answering. We experimentally evaluate the model on several datasets, such as MSRVTT-QA, MSVD-QA, IVQA. Our model reduces the required GFLOPs from 150-360 to only 67, producing a highly efficient video question answering model.
  arXiv  Detail & Related papers  (2022-08-01T15:35:38Z)
• VideoMix: Rethinking Data Augmentation for Video Classification [29.923635550986997]
  State-of-the-art video action classifiers often suffer from overfitting. Recent data augmentation strategies have been reported to address the overfitting problems. VideoMix lets a model learn beyond the object and scene biases and extract more robust cues for action recognition.
  arXiv  Detail & Related papers  (2020-12-07T05:40:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.