{"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/all-about-knowledge-graphs-for-actions","title":"All About Knowledge Graphs for Actions","arxiv_id":"2008.12432","date":"2020-08-28","proceeding":null,"authors":["Pallabi Ghosh","Nirat Saini","Larry S. Davis","Abhinav Shrivastava"],"abstract":"Current action recognition systems require large amounts of training data for recognizing an action. Recent works have explored the paradigm of zero-shot and few-shot learning to learn classifiers for unseen categories or categories with few labels. Following similar paradigms in object recognition, these approaches utilize external sources of knowledge (eg. knowledge graphs from language domains). However, unlike objects, it is unclear what is the best knowledge representation for actions. In this paper, we intend to gain a better understanding of knowledge graphs (KGs) that can be utilized for zero-shot and few-shot action recognition. In particular, we study three different construction mechanisms for KGs: action embeddings, action-object embeddings, visual embeddings. We present extensive analysis of the impact of different KGs in different experimental setups. Finally, to enable a systematic study of zero-shot and few-shot approaches, we propose an improved evaluation paradigm based on UCF101, HMDB51, and Charades datasets for knowledge transfer from models trained on Kinetics.","url_abs":"https://arxiv.org/abs/2008.12432v1","url_pdf":"https://arxiv.org/pdf/2008.12432v1.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":"all","task_name":"All"},{"task_slug":"few-shot-action-recognition","task_name":"Few Shot Action Recognition"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"few-shot-action-recognition","task_name":"Few-Shot action recognition"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"zero-shot-action-recognition","task_name":"Zero-Shot Action Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/zero-shot-action-recognition-on-kinetics","task":"Zero-Shot Action Recognition","dataset":"Kinetics","model":"GCN","rank_in_archive_order":19,"of":20,"metrics":{"Top-1 Accuracy":"22.3","Top-5 Accuracy":"49.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2008.12432","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}