Unbalanced optimal transport, from theory to numerics
Optimal Transport (OT) has recently emerged as a central tool in data sciences to compare
in a geometrically faithful way point clouds and more generally probability distributions. The …
in a geometrically faithful way point clouds and more generally probability distributions. The …
Does graph distillation see like vision dataset counterpart?
Training on large-scale graphs has achieved remarkable results in graph representation
learning, but its cost and storage have attracted increasing concerns. Existing graph …
learning, but its cost and storage have attracted increasing concerns. Existing graph …
Flot: Scene flow on point clouds guided by optimal transport
We propose and study a method called FLOT that estimates scene flow on point clouds. We
start the design of FLOT by noticing that scene flow estimation on point clouds reduces to …
start the design of FLOT by noticing that scene flow estimation on point clouds reduces to …
Graph optimal transport for cross-domain alignment
Cross-domain alignment between two sets of entities (eg, objects in an image, words in a
sentence) is fundamental to both computer vision and natural language processing. Existing …
sentence) is fundamental to both computer vision and natural language processing. Existing …
Collaborative filtering with attribution alignment for review-based non-overlapped cross domain recommendation
Cross-Domain Recommendation (CDR) has been popularly studied to utilize different
domain knowledge to solve the data sparsity and cold-start problem in recommender …
domain knowledge to solve the data sparsity and cold-start problem in recommender …
Delflow: Dense efficient learning of scene flow for large-scale point clouds
Point clouds are naturally sparse, while image pixels are dense. The inconsistency limits
feature fusion from both modalities for point-wise scene flow estimation. Previous methods …
feature fusion from both modalities for point-wise scene flow estimation. Previous methods …
Wasserstein embedding for graph learning
We present Wasserstein Embedding for Graph Learning (WEGL), a novel and fast
framework for embedding entire graphs in a vector space, in which various machine …
framework for embedding entire graphs in a vector space, in which various machine …
LICO: explainable models with language-image consistency
Interpreting the decisions of deep learning models has been actively studied since the
explosion of deep neural networks. One of the most convincing interpretation approaches is …
explosion of deep neural networks. One of the most convincing interpretation approaches is …
Deep learning for scene flow estimation on point clouds: A survey and prospective trends
Aiming at obtaining structural information and 3D motion of dynamic scenes, scene flow
estimation has been an interest of research in computer vision and computer graphics for a …
estimation has been an interest of research in computer vision and computer graphics for a …