PolySmart and VIREO @ TRECVid 2024 Ad-hoc Video Search

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wu, Jiaxin, Ngo, Chong-Wah, Wei, Xiao-Yong, Li, Qing
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910755783180288
author Wu, Jiaxin
Ngo, Chong-Wah
Wei, Xiao-Yong
Li, Qing
author_facet Wu, Jiaxin
Ngo, Chong-Wah
Wei, Xiao-Yong
Li, Qing
contents This year, we explore generation-augmented retrieval for the TRECVid AVS task. Specifically, the understanding of textual query is enhanced by three generations, including Text2Text, Text2Image, and Image2Text, to address the out-of-vocabulary problem. Using different combinations of them and the rank list retrieved by the original query, we submitted four automatic runs. For manual runs, we use a large language model (LLM) (i.e., GPT4) to rephrase test queries based on the concept bank of the search engine, and we manually check again to ensure all the concepts used in the rephrased queries are in the bank. The result shows that the fusion of the original and generated queries outperforms the original query on TV24 query sets. The generated queries retrieve different rank lists from the original query.
format Preprint
id arxiv_https___arxiv_org_abs_2412_15494
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PolySmart and VIREO @ TRECVid 2024 Ad-hoc Video Search
Wu, Jiaxin
Ngo, Chong-Wah
Wei, Xiao-Yong
Li, Qing
Information Retrieval
This year, we explore generation-augmented retrieval for the TRECVid AVS task. Specifically, the understanding of textual query is enhanced by three generations, including Text2Text, Text2Image, and Image2Text, to address the out-of-vocabulary problem. Using different combinations of them and the rank list retrieved by the original query, we submitted four automatic runs. For manual runs, we use a large language model (LLM) (i.e., GPT4) to rephrase test queries based on the concept bank of the search engine, and we manually check again to ensure all the concepts used in the rephrased queries are in the bank. The result shows that the fusion of the original and generated queries outperforms the original query on TV24 query sets. The generated queries retrieve different rank lists from the original query.
title PolySmart and VIREO @ TRECVid 2024 Ad-hoc Video Search
topic Information Retrieval
url https://arxiv.org/abs/2412.15494