{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/evolving-losses-for-unsupervised-video","title":"Evolving Losses for Unsupervised Video Representation Learning","arxiv_id":"2002.12177","date":"2020-02-26","proceeding":"CVPR 2020 6","authors":["AJ Piergiovanni","Anelia Angelova","Michael S. Ryoo"],"abstract":"We present a new method to learn video representations from large-scale unlabeled video data. Ideally, this representation will be generic and transferable, directly usable for new tasks such as action recognition and zero or few-shot learning. We formulate unsupervised representation learning as a multi-modal, multi-task learning problem, where the representations are shared across different modalities via distillation. Further, we introduce the concept of loss function evolution by using an evolutionary search algorithm to automatically find optimal combination of loss functions capturing many (self-supervised) tasks and modalities. Thirdly, we propose an unsupervised representation evaluation metric using distribution matching to a large unlabeled dataset as a prior constraint, based on Zipf's law. This unsupervised constraint, which is not guided by any labeling, produces similar results to weakly-supervised, task-specific ones. The proposed unsupervised representation learning results in a single RGB network and outperforms previous methods. Notably, it is also more effective than several label-based methods (e.g., ImageNet), with the exception of large, fully labeled video datasets.","url_abs":"https://arxiv.org/abs/2002.12177v1","url_pdf":"https://arxiv.org/pdf/2002.12177v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-action-recognition","task_name":"Self-Supervised Action Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/self-supervised-action-recognition-on-hmdb51","task":"Self-Supervised Action Recognition","dataset":"HMDB51","model":"ELo","rank_in_archive_order":19,"of":48,"metrics":{"Frozen":"false","Top-1 Accuracy":"64.5"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-action-recognition-on-hmdb51-1","task":"Self-Supervised Action Recognition","dataset":"HMDB51 (finetuned)","model":"ELo","rank_in_archive_order":6,"of":14,"metrics":{"Top-1 Accuracy":"67.4"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-action-recognition-on-ucf101-1","task":"Self-Supervised Action Recognition","dataset":"UCF101 (finetuned)","model":"ELo","rank_in_archive_order":4,"of":14,"metrics":{"3-fold Accuracy":"93.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2002.12177","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}