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

Considering the attacks against the power grid, one of the most effective
approaches could be the attack to the transmission lines that leads to large
cascading failures. Hence, the problem of locating the most critical or
vulnerable transmission lines for a Power Grid Cascading Failure (PGCF) has
drawn much attention from the research society. There exists many deterministic
solutions and stochastic approximation algorithms aiming to analyze the power
grid vulnerability. However, it has been challenging to reveal the correlations
between the transmission lines to identify the critical ones. In this paper, we
propose a novel approach of learning such correlations via attention mechanism
inspired by the Transformer based models that were initially designated to
learn the correlation of words in sentences. Multiple modifications and
adjustments are proposed to support the attention mechanism producing an
informative correlation matrix, the Attention Matrix. With the Attention
Ranking algorithm, we are able to identify the most critical lines. The
proposed Dual PGCF model provide a novel and effective analysis to improve the
power grid resilience against cascading failure, which is proved by extensive
experiment results.

提出了一种基于注意力机制的新方法来学习输电线路之间的相关性，并通过该方法识别最关键的输电线路，该方法通过 Attention Ranking 算法来评估输电线路的重要性，从而提供了一种改善电网对级联故障的韧性的新型有效分析，广泛的实验结果证明了其有效性。