D Zhao, Z Song, Z Ji, G Zhao… - Proceedings of the …, 2021 - openaccess.thecvf.com
Deep features have been proven powerful in building accurate dense semantic correspondences in various previous works. However, the multi-scale and pyramidal …
X Li, J Lu, K Han, VA Prisacariu - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
In this paper we address the challenge of matching semantically similar keypoints across image pairs. Existing research indicates that the intermediate output of the UNet within the …
Despite significant progress of deep learning in recent years, state-of-the-art semantic matching methods still rely on legacy features such as SIFT or HoG. We argue that the …
We address estimating dense correspondences between two images depicting different but semantically related scenes. End-to-end trainable deep neural networks incorporating …
Deep pre-trained language models (eg, BERT) lead to remarkable headway in many Natural Language Processing tasks. Their superior capacity in perceiving textual data is …
J Song, D Liang, R Li, Y Li, S Wang, M Peng… - arXiv preprint arXiv …, 2022 - arxiv.org
Transformer-based pre-trained models like BERT have achieved great progress on Semantic Sentence Matching. Meanwhile, dependency prior knowledge has also shown …
M Aygün, O Mac Aodha - European Conference on Computer Vision, 2022 - Springer
We explore semantic correspondence estimation through the lens of unsupervised learning. We thoroughly evaluate several recently proposed unsupervised methods across multiple …
S Hong, S Cho, S Kim, S Lin - The Twelfth International Conference …, 2024 - openreview.net
This paper introduces a Transformer-based integrative feature and cost aggregation network designed for dense matching tasks. In the context of dense matching, many works benefit …
This paper presents a deep architecture for dense semantic correspondence, called pyramidal affine regression networks (PARN), that estimates locally-varying affine …