A recent study published on arXiv investigates the alignment between video and text representations, marking a novel contribution to the field of multimodal learning. While prior research has extensively explored the relationship between images and text, this work is the first to comprehensively examine how video data integrates within this framework. The study sheds light on the structural similarities and capabilities shared by video and text modalities, providing new insights into their representational dynamics. This research builds on existing knowledge about image-text alignment but extends it by addressing the unique temporal and dynamic aspects of video content. By probing these video representations through text alignment, the study opens avenues for improved understanding and potential applications in video analysis and retrieval. The findings contribute to ongoing efforts to unify visual and linguistic data representations, enhancing the broader landscape of artificial intelligence research.