TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Datasets/VideoInstruct

VideoInstruct

Video Instruction Dataset

TextsVideosCreative Commons Attribution 4.0Introduced 2023-06-08

Video Instruction Dataset is used to train Video-ChatGPT. It consists of 100,000 high-quality video instruction pairs. employs a combination of human-assisted and semi-automatic annotation techniques, aiming to produce high-quality video instruction data. These methods create question-answer pairs related to

  1. Video summarization
  2. Description-based question-answers (exploring spatial, temporal, relationships, and reasoning concepts)
  3. Creative/generative question-answers

Benchmarks

Generative Visual Question Answering/meanGenerative Visual Question Answering/Correctness of InformationGenerative Visual Question Answering/Detail OrientationGenerative Visual Question Answering/Contextual UnderstandingGenerative Visual Question Answering/Temporal UnderstandingGenerative Visual Question Answering/ConsistencyGenerative Visual Question Answering/gpt-scoreVCGBench-Diverse/meanVCGBench-Diverse/Correctness of InformationVCGBench-Diverse/Detail OrientationVCGBench-Diverse/Contextual UnderstandingVCGBench-Diverse/Temporal UnderstandingVCGBench-Diverse/ConsistencyVCGBench-Diverse/Dense CaptioningVCGBench-Diverse/Spatial UnderstandingVCGBench-Diverse/ReasoningVideo-based Generative Performance Benchmarking/meanVideo-based Generative Performance Benchmarking/Correctness of InformationVideo-based Generative Performance Benchmarking/Detail OrientationVideo-based Generative Performance Benchmarking/Contextual UnderstandingVideo-based Generative Performance Benchmarking/Temporal UnderstandingVideo-based Generative Performance Benchmarking/ConsistencyVideo-based Generative Performance Benchmarking/gpt-scoreVideo-based Generative Performance Benchmarking (Correctness of Information)/gpt-scoreVisual Question Answering (VQA)/meanVisual Question Answering (VQA)/Correctness of InformationVisual Question Answering (VQA)/Detail OrientationVisual Question Answering (VQA)/Contextual UnderstandingVisual Question Answering (VQA)/Temporal UnderstandingVisual Question Answering (VQA)/ConsistencyVisual Question Answering (VQA)/gpt-score

Statistics

Papers
30
Benchmarks
31

Links

Homepage

Tasks

Generative Visual Question AnsweringVCGBench-DiverseVideo Question AnsweringVideo-based Generative Performance BenchmarkingVideo-based Generative Performance Benchmarking (Consistency)Video-based Generative Performance Benchmarking (Contextual Understanding)Video-based Generative Performance Benchmarking (Correctness of Information)Video-based Generative Performance Benchmarking (Detail Orientation))Video-based Generative Performance Benchmarking (Temporal Understanding)Visual Question Answering (VQA)