{"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/d2-net-weakly-supervised-action-localization","title":"D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations","arxiv_id":"2012.06440","date":"2020-12-11","proceeding":"ICCV 2021 10","authors":["Sanath Narayan","Hisham Cholakkal","Munawar Hayat","Fahad Shahbaz Khan","Ming-Hsuan Yang","Ling Shao"],"abstract":"This work proposes a weakly-supervised temporal action localization framework, called D2-Net, which strives to temporally localize actions using video-level supervision. Our main contribution is the introduction of a novel loss formulation, which jointly enhances the discriminability of latent embeddings and robustness of the output temporal class activations with respect to foreground-background noise caused by weak supervision. The proposed formulation comprises a discriminative and a denoising loss term for enhancing temporal action localization. The discriminative term incorporates a classification loss and utilizes a top-down attention mechanism to enhance the separability of latent foreground-background embeddings. The denoising loss term explicitly addresses the foreground-background noise in class activations by simultaneously maximizing intra-video and inter-video mutual information using a bottom-up attention mechanism. As a result, activations in the foreground regions are emphasized whereas those in the background regions are suppressed, thereby leading to more robust predictions. Comprehensive experiments are performed on multiple benchmarks, including THUMOS14 and ActivityNet1.2. Our D2-Net performs favorably in comparison to the existing methods on all datasets, achieving gains as high as 2.3% in terms of mAP at IoU=0.5 on THUMOS14. Source code is available at https://github.com/naraysa/D2-Net","url_abs":"https://arxiv.org/abs/2012.06440v2","url_pdf":"https://arxiv.org/pdf/2012.06440v2.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":[{"paper_slug":"d2-net-weakly-supervised-action-localization","repo_url":"https://github.com/naraysa/D2-Net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"action-localization","task_name":"Action Localization"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"weakly-supervised-action-localization","task_name":"Weakly Supervised Action Localization"},{"task_slug":"weakly-supervised-temporal-action","task_name":"Weakly-supervised Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-action-localization-on-2","task":"Weakly Supervised Action Localization","dataset":"ActivityNet-1.2","model":"D2-Net","rank_in_archive_order":8,"of":19,"metrics":{"Mean mAP":"26","mAP@0.5":"42.3"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-action-localization-on-7","task":"Weakly Supervised Action Localization","dataset":"FineAction","model":"D2-Net","rank_in_archive_order":3,"of":4,"metrics":{"mAP":"3.35","mAP IOU@0.5":"6.75","mAP IOU@0.75":"3.02","mAP IOU@0.95":"0.82"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-action-localization-on","task":"Weakly Supervised Action Localization","dataset":"THUMOS 2014","model":"D2-Net","rank_in_archive_order":23,"of":30,"metrics":{"mAP@0.1:0.5":"51.4","mAP@0.1:0.7":"-","mAP@0.5":"35.9"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-action-localization-on-4","task":"Weakly Supervised Action Localization","dataset":"THUMOS’14","model":"D2-Net","rank_in_archive_order":4,"of":13,"metrics":{"mAP@0.5":"35.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2012.06440","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}