Evaluating visual "common sense" using fine-grained classification and captioning tasksDownload PDF

12 Feb 2018 (modified: 05 May 2023)ICLR 2018 Workshop SubmissionReaders: Everyone
Abstract: We introduce the Something-something V2 dataset, which contains captions of finely-varying human-object interactions. We also discuss various baseline models, and show that neural networks show surprisingly strong performance on many of the very hard, detailed discrimination tasks associated with this dataset.
Keywords: video dataset, fine-grained understanding, common sense, video captioning
4 Replies