Recent studies show that leveraging the match-wise relationships within the 4D correlation
map yields significant improvements in establishing semantic correspondences-but at the …

Deep features have been proven powerful in building accurate dense semantic
correspondences in various previous works. However, the multi-scale and pyramidal …

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 …

Transformer-based pre-trained models like BERT have achieved great progress on
Semantic Sentence Matching. Meanwhile, dependency prior knowledge has also shown …

We explore semantic correspondence estimation through the lens of unsupervised learning.
We thoroughly evaluate several recently proposed unsupervised methods across multiple …

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 …