Towards semantic, debiased and moment video retrieval
Video retrieval aims to retrieve a whole video within a video corpus given a language query. However, one of the main challenges is that it requires reaching a semantic correlation between these modalities. Besides, imbalanced datasets can cause biases in the retrieval models. Moreover, retrieving a...
Saved in:
Main Author: | Satar, Burak |
---|---|
Other Authors: | - |
Format: | Thesis-Doctor of Philosophy |
Language: | English |
Published: |
Nanyang Technological University
2025
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/182104 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Cross-modal Moment Localization in Videos
by: Meng Liu, et al.
Published: (2020) -
Temporal sentence grounding in videos: a survey and future directions
by: Zhang, Hao, et al.
Published: (2023) -
Attentive Moment Retrieval in Videos
by: Meng Liu, et al.
Published: (2020) -
Efficient cross-modal video retrieval with meta-optimized frames
by: HAN, Ning, et al.
Published: (2024) -
VRAG: Region Attention Graph for Content-Based Video Retrieval
by: KENNARD NG POOL HUA
Published: (2021)