Pith. sign in

REVIEW 1 cited by

Egocentric Video-Language Pretraining @ EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2207.01334 v2 pith:SVZHIJD6 submitted 2022-07-04 cs.CV

Kevin Qinghong Lin , Alex Jinpeng Wang , Rui Yan , Eric Zhongcong Xu , Rongcheng Tu , Yanru Zhu , Wenzhe Zhao , Weijie Kong
show 4 more authors
Chengfei Cai Hongfa Wang Wei Liu Mike Zheng Shou
This is my paper · ORCID
classification cs.CV
keywords pretrainingchallengeegocentricmodelmulti-instancevideo-languagecitedataset
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this report, we propose a video-language pretraining (VLP) based solution \cite{kevin2022egovlp} for the EPIC-KITCHENS-100 Multi-Instance Retrieval (MIR) challenge. Especially, we exploit the recently released Ego4D dataset \cite{grauman2021ego4d} to pioneer Egocentric VLP from pretraining dataset, pretraining objective, and development set. Based on the above three designs, we develop a pretrained video-language model that is able to transfer its egocentric video-text representation to MIR benchmark. Furthermore, we devise an adaptive multi-instance max-margin loss to effectively fine-tune the model and equip the dual-softmax technique for reliable inference. Our best single model obtains strong performance on the challenge test set with 47.39% mAP and 61.44% nDCG. The code is available at https://github.com/showlab/EgoVLP.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. EVA02-AT: Egocentric Video-Language Understanding with Spatial-Temporal Rotary Positional Embeddings and Symmetric Optimization

    cs.CV 2025-06 conditional novelty 5.0 of 10

    EVA02-AT combines full-dimension spatial and temporal rotary position embeddings with a symmetric multi-similarity loss to improve egocentric video-text retrieval.

Pith tools