Pey88/MVBench
收藏资源简介:
--- license: mit extra_gated_prompt: >- You agree to not use the dataset to conduct experiments that cause harm to human subjects. Please note that the data in this dataset may be subject to other agreements. Before using the data, be sure to read the relevant agreements carefully to ensure compliant use. Video copyrights belong to the original video creators or platforms and are for academic research use only. task_categories: - visual-question-answering - video-classification extra_gated_fields: Name: text Company/Organization: text Country: text E-Mail: text modalities: - Video - Text configs: - config_name: action_sequence data_files: json/action_sequence.json - config_name: moving_count data_files: json/moving_count.json - config_name: action_prediction data_files: json/action_prediction.json - config_name: episodic_reasoning data_files: json/episodic_reasoning.json - config_name: action_antonym data_files: json/action_antonym.json - config_name: action_count data_files: json/action_count.json - config_name: scene_transition data_files: json/scene_transition.json - config_name: object_shuffle data_files: json/object_shuffle.json - config_name: object_existence data_files: json/object_existence.json - config_name: fine_grained_pose data_files: json/fine_grained_pose.json - config_name: unexpected_action data_files: json/unexpected_action.json - config_name: moving_direction data_files: json/moving_direction.json - config_name: state_change data_files: json/state_change.json - config_name: object_interaction data_files: json/object_interaction.json - config_name: character_order data_files: json/character_order.json - config_name: action_localization data_files: json/action_localization.json - config_name: counterfactual_inference data_files: json/counterfactual_inference.json - config_name: fine_grained_action data_files: json/fine_grained_action.json - config_name: moving_attribute data_files: json/moving_attribute.json - config_name: egocentric_navigation data_files: json/egocentric_navigation.json language: - en size_categories: - 1K<n<10K --- # MVBench ## Dataset Description - **Repository:** [MVBench](https://github.com/OpenGVLab/Ask-Anything/blob/main/video_chat2/mvbench.ipynb) - **Paper:** [2311.17005](https://arxiv.org/abs/2311.17005) - **Point of Contact:** mailto:[kunchang li](likunchang@pjlab.org.cn) ## <span style="color: red;">Important Update</span> [18/10/2024] Due to NTU RGB+D License, 320 videos from NTU RGB+D need to be downloaded manually. Please visit [ROSE Lab](https://rose1.ntu.edu.sg/dataset/actionRecognition/) to access the data. We also provide a [list of the 320 videos](https://huggingface.co/datasets/OpenGVLab/MVBench/blob/main/video/MVBench_videos_ntu.txt) used in MVBench for your reference.  We introduce a novel static-to-dynamic method for defining temporal-related tasks. By converting static tasks into dynamic ones, we facilitate systematic generation of video tasks necessitating a wide range of temporal abilities, from perception to cognition. Guided by task definitions, we then **automatically transform public video annotations into multiple-choice QA** for task evaluation. This unique paradigm enables efficient creation of MVBench with minimal manual intervention while ensuring evaluation fairness through ground-truth video annotations and avoiding biased LLM scoring. The **20** temporal task examples are as follows.  ## Evaluation An evaluation example is provided in [mvbench.ipynb](https://github.com/OpenGVLab/Ask-Anything/blob/main/video_chat2/mvbench.ipynb). Please follow the pipeline to prepare the evaluation code for various MLLMs. - **Preprocess**: We preserve the raw video (high resolution, long duration, etc.) along with corresponding annotations (start, end, subtitles, etc.) for future exploration; hence, the decoding of some raw videos like Perception Test may be slow. - **Prompt**: We explore effective system prompts to encourage better temporal reasoning in MLLM, as well as efficient answer prompts for option extraction. ## Leadrboard While an [Online leaderboard]() is under construction, the current standings are as follows: 
许可证:MIT extra_gated_prompt: >- 您同意不得使用本数据集开展会对人类受试者造成伤害的实验。请注意本数据集内的数据可能受其他协议约束。在使用数据前,请务必仔细阅读相关协议以确保合规使用。视频版权归原视频创作者或平台所有,仅可用于学术研究用途。 task_categories: - 视觉问答(visual-question-answering) - 视频分类(video-classification) extra_gated_fields: 姓名:文本 公司/组织:文本 国家:文本 电子邮箱(E-Mail):文本 modalities: - 视频(Video) - 文本(Text) configs: - 配置名称:动作序列(action_sequence),数据文件:json/action_sequence.json - 配置名称:移动计数(moving_count),数据文件:json/moving_count.json - 配置名称:动作预测(action_prediction),数据文件:json/action_prediction.json - 配置名称:情景推理(episodic_reasoning),数据文件:json/episodic_reasoning.json - 配置名称:动作反义(action_antonym),数据文件:json/action_antonym.json - 配置名称:动作计数(action_count),数据文件:json/action_count.json - 配置名称:场景转换(scene_transition),数据文件:json/scene_transition.json - 配置名称:物体洗牌(object_shuffle),数据文件:json/object_shuffle.json - 配置名称:物体存在性(object_existence),数据文件:json/object_existence.json - 配置名称:细粒度姿态(fine_grained_pose),数据文件:json/fine_grained_pose.json - 配置名称:意外动作(unexpected_action),数据文件:json/unexpected_action.json - 配置名称:移动方向(moving_direction),数据文件:json/moving_direction.json - 配置名称:状态变化(state_change),数据文件:json/state_change.json - 配置名称:物体交互(object_interaction),数据文件:json/object_interaction.json - 配置名称:角色顺序(character_order),数据文件:json/character_order.json - 配置名称:动作定位(action_localization),数据文件:json/action_localization.json - 配置名称:反事实推理(counterfactual_inference),数据文件:json/counterfactual_inference.json - 配置名称:细粒度动作(fine_grained_action),数据文件:json/fine_grained_action.json - 配置名称:移动属性(moving_attribute),数据文件:json/moving_attribute.json - 配置名称:以自我为中心的导航(egocentric_navigation),数据文件:json/egocentric_navigation.json language: - 英语 size_categories: - 1K<n<10K --- # MVBench ## 数据集简介 - **仓库地址**:[MVBench](https://github.com/OpenGVLab/Ask-Anything/blob/main/video_chat2/mvbench.ipynb) - **论文链接**:[2311.17005](https://arxiv.org/abs/2311.17005) - **联系方式**:mailto:[李昌坤(Kunchang Li)](likunchang@pjlab.org.cn) ## <span style="color: red;">重要更新</span> [2024年10月18日] 由于NTU RGB+D许可证要求,需手动下载NTU RGB+D数据集中的320个视频。请访问[ROSE实验室(ROSE Lab)](https://rose1.ntu.edu.sg/dataset/actionRecognition/)获取数据。我们还提供了MVBench中使用的320个视频的[列表](https://huggingface.co/datasets/OpenGVLab/MVBench/blob/main/video/MVBench_videos_ntu.txt)供您参考。  我们提出了一种全新的静态转动态方法用于定义时序相关任务。通过将静态任务转换为动态任务,我们得以系统性生成涵盖从感知到认知等广泛时序能力需求的视频任务。在任务定义的指导下,我们**自动将公开视频标注转换为多项选择题问答(QA)形式**以用于任务评估。这一独特范式能够在最小人工干预的前提下高效构建MVBench数据集,同时通过真实视频标注确保评估公平性,并避免大语言模型(LLM)评分带来的偏差。本次共展示20个时序任务示例。  ## 评估 评估示例可参见[mvbench.ipynb](https://github.com/OpenGVLab/Ask-Anything/blob/main/video_chat2/mvbench.ipynb)。请按照该流程为各类多模态大语言模型(MLLM)准备评估代码。 - **预处理**:我们保留了原始视频(高分辨率、长时长等)及对应标注信息(起始时间、结束时间、字幕等)以供后续研究;因此部分原始视频(如Perception Test)的解码过程可能较慢。 - **提示词设计**:我们探索了可有效激发多模态大语言模型时序推理能力的系统提示词,以及用于选项提取的高效答案提示词。 ## 排行榜 目前[在线排行榜]()正在开发中,当前排名如下: 




