Pre-trained vision transformers have strong representation benefits to
v...
The prevalence of short video platforms has spawned a lot of fake news
v...
The text-driven image and video diffusion models have achieved unprecede...
Parameter-Efficient Transfer Learning (PETL) aims at efficiently adaptin...
Domain shift widely exists in the visual world, while modern deep neural...
Semantic segmentation in 3D indoor scenes has achieved remarkable perfor...
Given a graph G, a query node q, and an integer k, community search
(CS)...
In this paper, we consider the problem of domain generalization in seman...
In this paper, we study the task of synthetic-to-real domain generalized...
We introduce a new setting of Novel Class Discovery in Semantic Segmenta...
In this work, we introduce a new concept, named source-free open compoun...
Recent advances in person re-identification (ReID) obtain impressive acc...
In this paper, we propose a spatio-temporal contextual network, STC-Flow...