In this report, we present our champion solution for EPIC-KITCHENS-100
Multi-Instance Retrieval Challenge in CVPR 2024. Essentially, this challenge
differs from traditional visual-text retrieval tasks by providing a correlation
matrix that acts as a set of soft labels for video-text clip combinations.
However, existing loss functions have not fully exploited this information.
Motivated by this, we propose a novel loss function, Symmetric Multi-Similarity
Loss, which offers a more precise learning objective. Together with tricks and
ensemble learning, the model achieves 63.76% average mAP and 74.25% average
nDCG on the public leaderboard, demonstrating the effectiveness of our
approach. Our code will be released at:
this https URL

我们在 CVPR 2024 的 EPIC-KITCHENS-100 多实例检索挑战中提出了一种新的损失函数 —— 对称多相似性损失，通过与技巧和集成学习相结合，模型在公共排行榜上获得了 63.76% 平均 mAP 和 74.25% 平均 nDCG 的表现，展示了方法的有效性。

EPIC-KITCHENS-100 多例检索挑战 2024 的对称多相似性损失

Symmetric Multi-Similarity Loss for EPIC-KITCHENS-100 Multi-Instance  Retrieval Challenge 2024

In this report, we present the technical details of our submission to the
EPIC-Kitchens-100 Multi-Instance Retrieval Challenge 2023. To participate in
the challenge, we ensembled two models trained with two different loss
functions on 25% of the training data. Our submission, visible on the public
leaderboard, obtains an average score of 56.81% nDCG and 42.63% mAP.

该研究报告介绍了作者参加 EPIC-Kitchens-100 多实例检索挑战的技术细节和实验结果，使用不同损失函数对 25％的训练数据进行了两个模型的集成，并获得了 56.81％的 nDCG 和 42.63％的 mAP 的平均分数。