The video filename is a specific clip from the Something-Something V2 dataset [1, 3]. This dataset is widely used in computer vision research to train models on human-object interactions and temporal reasoning [2, 4].
Something-Something V2, which contains over 220,000 video clips [3]. g60917.mp4
In this dataset, "g60917.mp4" typically represents a specific label, such as "Pushing [something] so that it falls off the table" or a similar interaction, depending on the specific version's indexing [1, 4]. The video filename is a specific clip from
If you are looking for this file, you are likely working with one of the following state-of-the-art models that use this dataset for benchmarking: 4]. Something-Something V2
: Applying transformer architectures to video recognition.