Symmetric Multi-Similarity Loss for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2024
Not on the map. Why?
Abstract (arXiv)
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: https://github.com/xqwang14/SMS-Loss/tree/main
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 11 of its 13 references that are in the map. First posted on arXiv 18 Jun 2024.
Builds on
11 of 13 references.
References · 11
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,530
- 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 789
- 2020Rescaling Egocentric Visioncited by 529
- 2019Multi-Similarity Loss with General Pair Weighting for Deep Metric Learningcited by 368
- 2022Egocentric Video-Language Pretrainingcited by 231
- 2019Joint Discriminative and Generative Learning for Person Re-identificationcited by 211
- 2022Learning Video Representations from Large Language Modelscited by 204
- 2019Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddingscited by 101
- 2024DGL: Dynamic Global-Local Prompt Tuning for Text-Video Retrievalcited by 26
- 2023Training a Large Video Model on a Single Machine in a Daycited by 20
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.