Self-supervised learning has gained popularity because of its ability to avoid the cost of annotating large-scale datasets. It is capable of adopting self-defined pseudolabels as supervision and use the learned representations for several downstream tasks. Specifically, contrastive learning has recently become a dominant component in self-supervised learning for computer vision, natural language processing (NLP), and other domains. It aims at embedding augmented versions of the same sample close to each other while trying to push away embeddings from different samples. This paper provides an eResearch goal: How do different auxiliary objective variants in Video-JEPA affect downstream task performance when fine-tuned on the UCF-101 and Something-Something V2 benchmarks, measured by classification accuracy?Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.2/10.