LLM-based query paraphrasing for video search

J Wu, CW Ngo, WK Chan, SH Zhong - arXiv preprint arXiv:2407.12341, 2024 - arxiv.org
Text-to-video retrieval answers user queries through search by concepts and embeddings.
Limited by the size of the concept bank and the amount of training data, answering queries …

Improving Interpretable Embeddings for Ad-hoc Video Search with Generative Captions and Multi-word Concept Bank

J Wu, CW Ngo, WK Chan - … of the 2024 International Conference on …, 2024 - dl.acm.org
Aligning a user query and video clips in cross-modal latent space and that with semantic
concepts are two mainstream approaches for ad-hoc video search (AVS). However, the …

[PDF][PDF] Waseda meisei softbank at TRECVID 2022

K Ueki, Y Suzuki, H Takushima… - Proceedings of the …, 2022 - www-nlpir.nist.gov
The Waseda Meisei SoftBank team participated in the ad-hoc video search (AVS), video-to-
text (VTT), and activities in extended video (ActEV) tasks at TRECVID 2022 [1]. For this …

Cliprerank: An Extremely Simple Method For Improving Ad-Hoc Video Search

A Chen, F Zhou, Z Wang, X Li - ICASSP 2024-2024 IEEE …, 2024 - ieeexplore.ieee.org
Ad-hoc Video Search (AVS) enables users to search for unlabeled video content using on-
the-fly textual queries. Current deep learning-based models for AVS are trained to optimize …

[PDF][PDF] DEEP-CAM: Attention based Multi-modal Deep Learning Models for Medical Instructional Question Generation

S Saha, S Purushotham - www-nlpir.nist.gov
This paper describes the participation of the UMBCVQA team in the Medical Instructional
Question Generation (MIQG) task of the MedVidQA challenge at TREC Video Retrieval …

[PDF][PDF] ITI-CERTH participation in AVS Task of TRECVID 2023

This report presents an overview of the runs submitted to Ad-hoc Video Search (AVS) on
behalf of the ITI-CERTH team. Our participation in the AVS task is based on a transformer …

[PDF][PDF] UNCWAI at MedVidQA 2023: T5 Model for Video Temporal Segment Prediction

L Qi, O Deen, ZF Xie, X Cui, G Dogan - www-nlpir.nist.gov
In this paper, we present our solution to the Med-VidQA 2023 Task 1: Video Corpus Visual
Answer Localization. We used the training and testing datasets provided by the MedVidQA …

[PDF][PDF] Renmin University of China and Tencent at TRECVID 2023: Harnessing Pre-trained Models for Ad-hoc Video Search

X Li, F Hu, R Zhao, Z Wang, J Liu, J Liu, B Lan, W Kou… - www-nlpir.nist.gov
We summarize our TRECVID 2023 Ad-hoc Video Search (AVS) experiments. We focus on
leveraging pre-trained multimodal models for video and text representation. For video …

[PDF][PDF] Doshisha University, Universität zu Lübeck and German Research Center for Artificial Intelligence at TRECVID 2023: MIQG Task

Z Chen, F Li, MS Seibel, NS Brügge, M Ohsaki… - www-nlpir.nist.gov
This paper presents the approaches proposed by the doshisha_uzl team to address the
Medical Instructional Question Generation (MIQG) task of TRECVID 2023. Given a clip from …