Code Issues Pull requests Cross Modal Retrieval with Querybank Normalisation image video retrieval text softmax normalisation t2v dynamic-softmax inverted-softmax querybank Updated Nov 21, 2023 Python ColumbiaDVMM / Heated_Up_Softmax_Embedding Star 43 Code Issues Pull requests Project page for...
Source code of our AAAI 2024 paper "Cross-Modal and Uni-Modal Soft-Label Alignment for Image-Text Retrieval" - lerogo/aaai24_itr_cusa
Contrastive representation learning has proven to be an effective self-supervised learning method for images and videos. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as positives that should be contrasted with other instances, called ...
To solve these problems, in this paper, we propose a novel approach, Soft Contrastive Cross-Modal Retrieval (SCCMR), which integrates the deep cross-modal model with soft contrastive learning and smooth label cross-entropy learning to boost common subspace embedding and improve the generalizability ...