Neural scene representations, both continuous and discrete, have recentl...
Rotation equivariance has recently become a strongly desired property in...
Writer identification (writer-id), an important field in biometrics, aim...
We study the problem of inferring an object-centric scene representation...
We present a method, Neural Radiance Flow (NeRFlow),to learn a 4D
spatia...
Large-scale photorealistic datasets of indoor scenes, with ground truth
...
Unsupervised learning of identity-discriminative visual feature is appea...
We focus on explicitly learning disentangled representation for natural ...
Although unsupervised person re-identification (RE-ID) has drawn increas...
Person re-identification (Re-ID) aims to match identities across
non-ove...
In this work, we present an interesting attempt on mixture generation:
a...
Attribute based person re-identification (Re-ID) aims to search persons ...
While metric learning is important for Person re-identification (RE-ID),...