The "g60104" identifier is part of the or GTEA Gaze+ datasets, which are used to evaluate computer vision models on:

Mapping where a subject is looking while performing a task. Where to Access ArXiv: You can read the full methodology and results here.

If you are looking for the raw video file itself for testing, it is typically hosted on the Georgia Tech FovLab website under the GTEA dataset sections.

Identifying specific tasks like "folding a tortilla" or "pouring water."

This work is frequently cited in the context of the KTH Action Dataset , where video files follow similar alphanumeric naming conventions. Context of the Video

Deep Video Generation, Prediction and Completion of Human Action Sequences Authors: Haotian Xue, Wenqing Chu, Zhao-Jie Ju, et al.