MoCap-Video Data Retrieval with Deep Cross-Modal Learning
L Zhang, J Peng, N Lv - International Conference on Multimedia Modeling, 2024 - Springer
Cross-modal retrieval between video and motion capture (MoCap) data facilitates efficient
reuse of human motion data in either skeletal or video format. For this purpose, we propose …
reuse of human motion data in either skeletal or video format. For this purpose, we propose …
Text-based Audio Retrieval by Learning from Similarities between Audio Captions
H Xie, K Khorrami, O Räsänen… - IEEE Signal Processing …, 2024 - ieeexplore.ieee.org
This letter proposes to use similarities of audio captions for estimating audio-caption
relevances to be used for training text-based audio retrieval systems. Current audio-caption …
relevances to be used for training text-based audio retrieval systems. Current audio-caption …
Dynamic Soft Labeling for Visual Semantic Embedding
Visual Semantic Embedding (VSE) is a prominent approach in image-text retrieval, aiming to
learn a deep embedding space that aligns visual data with semantic text labels. However …
learn a deep embedding space that aligns visual data with semantic text labels. However …
A Review on the Progress of Text-based Image Retrieval Technology
R Ma, X Cui, W Li, L Lu - Advances in Engineering …, 2024 - madison-proceedings.com