# Exploiting Semantic Role Contextualized Video Features for Multi-Instance Text-Video Retrieval EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022

arXiv: https://arxiv.org/abs/2206.14381 · HTML: https://mlsanity.com/paper/2206.14381/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 15 references that are in the map.
- First posted on arXiv 29 Jun 2022.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Rescaling Egocentric Vision](https://mlsanity.com/paper/2006.13256/) (2020)
- [End-to-End Learning of Visual Representations from Uncurated Instructional Videos](https://mlsanity.com/paper/1912.06430/) (2019)
- [Multi-modal Transformer for Video Retrieval](https://mlsanity.com/paper/2007.10639/) (2020)
- [EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition](https://mlsanity.com/paper/1908.08498/) (2019)
- [Use What You Have: Video Retrieval Using Representations From Collaborative Experts](https://mlsanity.com/paper/1907.13487/) (2019)
- [Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning](https://mlsanity.com/paper/2003.00392/) (2020)
- [Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings](https://mlsanity.com/paper/1908.03477/) (2019)
- [Dual Encoding for Zero-Example Video Retrieval](https://mlsanity.com/paper/1809.06181/) (2018)
- [On Semantic Similarity in Video Retrieval](https://mlsanity.com/paper/2103.10095/) (2021)
- [RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval](https://mlsanity.com/paper/2206.12845/) (2022)
- [Semantic Role Aware Correlation Transformer for Text to Video Retrieval](https://mlsanity.com/paper/2206.12849/) (2022)

## Built on by (most cited first, 5 of 5)

- [Seeing Culture: A Benchmark for Visual Reasoning and Grounding](https://mlsanity.com/paper/2509.16517/) (2025)
- [An Overview of Challenges in Egocentric Text-Video Retrieval](https://mlsanity.com/paper/2306.04345/) (2023)
- [UniUD Submission to the EPIC-Kitchens-100 Multi-Instance Retrieval Challenge 2023](https://mlsanity.com/paper/2306.15445/) (2023)
- [Towards Debiasing Frame Length Bias in Text-Video Retrieval via Causal Intervention](https://mlsanity.com/paper/2309.09311/) (2023)
- [Cultural Moment Benchmark: Evaluating Video Cultural Reasoning and Grounding in Southeast Asia](https://mlsanity.com/paper/2608.23065/) (2026)

## Abstract (arXiv)

In this report, we present our approach for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022. We first parse sentences into semantic roles corresponding to verbs and nouns; then utilize self-attentions to exploit semantic role contextualized video features along with textual features via triplet losses in multiple embedding spaces. Our method overpasses the strong baseline in normalized Discounted Cumulative Gain (nDCG), which is more valuable for semantic similarity. Our submission is ranked 3rd for nDCG and ranked 4th for mAP.