G60917.mp4 Apr 2026

Something-Something V2, which contains over 220,000 video clips [3].

: Efficient video understanding [4].

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]. g60917.mp4

by Raghav Goyal, Samira Ebrahimi Kahou, Raul Vazquez, Christian Rousseau, Nicolas Ballas, Laurent Charlin, and Roland Memisevic (2017) [2, 5]. Context of the Video which contains over 220

: Learning temporal aspects of video via self-attention. "g60917.mp4" typically represents a specific label

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:

: Applying transformer architectures to video recognition.