UniUD-FBK-UB-UniBZ Submission to the EPIC-Kitchens-100 Multi-Instance Retrieval Challenge 2022
Not on the map. Why?
Abstract (arXiv)
This report presents the technical details of our submission to the EPIC-Kitchens-100 Multi-Instance Retrieval Challenge 2022. To participate in the challenge, we designed an ensemble consisting of different models trained with two recently developed relevance-augmented versions of the widely used triplet loss. Our submission, visible on the public leaderboard, obtains an average score of 61.02% nDCG and 49.77% mAP.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 8 of its 9 references that are in the map. First posted on arXiv 22 Jun 2022.
Builds on
8 of 9 references.
References · 8
- 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
- 2020Rescaling Egocentric Visioncited by 529
- 2019EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognitioncited by 226
- 2020Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoningcited by 180
- 2019Simple BERT Models for Relation Extraction and Semantic Role Labelingcited by 154
- 2019Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddingscited by 101
- 2022Learning video retrieval models with relevance-aware online miningcited by 6
- 2022Relevance-based Margin for Contrastively-trained Video Retrieval Modelscited by 6
Built on by
Citing papers per year: 2023: 1.
1 paper.