{"url":"/dataset/vcg-112k","name":"VCG+112K","full_name":"Video Instruction Dataset 112K","description_markdown":"Video-ChatGPT introduces the VideoInstruct100K dataset, which employs a semi-automatic annotation pipeline to generate 75K instruction-tuning QA pairs. To address the limitations of this annotation process, we present \\ourdata~dataset developed through an improved annotation pipeline. Our approach improves the accuracy and quality of instruction tuning pairs by improving keyframe extraction, leveraging SoTA large multimodal models (LMMs) for detailed descriptions, and refining the instruction generation strategy.","description_withheld":null,"homepage":"https://huggingface.co/datasets/MBZUAI/VCG-plus_112K","introduced_date":"2024-06-13","introduced_date_note":null,"introduced_by":{"paper":"/paper/videogpt-integrating-image-and-video-encoders","title":"VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding","first_author":"Muhammad Maaz","url":null},"license":{"name":"MIT","url":"https://opensource.org/license/mit"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Video Question Answering","url":"/task/video-question-answering","datasets_with_task":"/datasets/task/video-question-answering"},{"name":"Video Understanding","url":"/task/video-understanding","datasets_with_task":"/datasets/task/video-understanding"},{"name":"Video-based Generative Performance Benchmarking","url":"/task/video-based-generative-performance","datasets_with_task":"/datasets/task/video-based-generative-performance"},{"name":"Zeroshot Video Question Answer","url":"/task/zeroshot-video-question-answer-1","datasets_with_task":"/datasets/task/zeroshot-video-question-answer-1"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["VCG+112K"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}