arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2502.17753cs.CV

任务图最大似然估计用于第一视角视频中的程序性活动理解

Task Graph Maximum Likelihood Estimation for Procedural Activity Understanding in Egocentric Videos

University of Catania(卡塔尼亚大学)

Luigi Seminara, Giovanni Maria Farinella, Antonino Furnari

AI总结:

提出基于梯度的任务图最大似然学习方法,直接优化边权重,在多个基准上显著提升F1分数,并改进在线错误检测。

摘要:

我们提出了一种基于梯度的学习方法,用于从程序性活动中学习任务图,改进了手工设计的方法。我们的方法通过最大似然直接优化边权重,使其能够集成到神经架构中。我们在CaptainCook4D、EgoPER和EgoProceL上验证了我们的方法,分别取得了+14.5%、+10.2%和+13.6%的F1分数提升。我们基于特征的方法从文本/视频嵌入中预测任务图,展现出新兴的视频理解能力。我们还在Ego-Exo4D上的程序理解基准测试中取得了最佳性能,并显著改进了在线错误检测(在Assembly101-O上提升+19.8%,在EPIC-Tent-O上提升+6.4%)。代码:https://github.com/fpv-iplab/Differentiable-Task-Graph-Learning。

英文摘要:

We introduce a gradient-based approach for learning task graphs from procedural activities, improving over hand-crafted methods. Our method directly optimizes edge weights via maximum likelihood, enabling integration into neural architectures. We validate our approach on CaptainCook4D, EgoPER, and EgoProceL, achieving +14.5%, +10.2%, and +13.6% F1-score improvements. Our feature-based approach for predicting task graphs from textual/video embeddings demonstrates emerging video understanding abilities. We also achieved top performance on the procedure understanding benchmark on Ego-Exo4D and significantly improved online mistake detection (+19.8% on Assembly101-O, +6.4% on EPIC-Tent-O). Code: https://github.com/fpv-iplab/Differentiable-Task-Graph-Learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑