The reviewed record of science sign in
Pith

arxiv: 2211.08776 · v1 · pith:5DDYIAG6 · submitted 2022-11-16 · cs.CV · cs.IR

An Efficient COarse-to-fiNE Alignment Framework @ Ego4D Natural Language Queries Challenge 2022

Reviewed by Pithpith:5DDYIAG6open to challenge →

classification cs.CV cs.IR
keywords conealignmentcandidatewindowsapproachchallengecoarse-to-finecontrastive
0
0 comments X
read the original abstract

This technical report describes the CONE approach for Ego4D Natural Language Queries (NLQ) Challenge in ECCV 2022. We leverage our model CONE, an efficient window-centric COarse-to-fiNE alignment framework. Specifically, CONE dynamically slices the long video into candidate windows via a sliding window approach. Centering at windows, CONE (1) learns the inter-window (coarse-grained) semantic variance through contrastive learning and speeds up inference by pre-filtering the candidate windows relevant to the NL query, and (2) conducts intra-window (fine-grained) candidate moments ranking utilizing the powerful multi-modal alignment ability of the contrastive vision-text pre-trained model EgoVLP. On the blind test set, CONE achieves 15.26 and 9.24 for R1@IoU=0.3 and R1@IoU=0.5, respectively.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.