Optical flow is an easily conceived and precious cue for advancing
unsup...
Person Re-Identification (ReID) matches pedestrians across disjoint came...
Semantic segmentation aims to classify every pixel of an input image.
Co...
Due to the memorization effect in Deep Neural Networks (DNNs), training ...
One-shot semantic image segmentation aims to segment the object regions ...
Labeling objects at a subordinate level typically requires expert knowle...
Constructing fine-grained image datasets typically requires domain-speci...
Recent successes in visual recognition can be primarily attributed to fe...
Person re-identification aims to establish the correct identity
correspo...
Robust road segmentation is a key challenge in self-driving research. Th...
Person re-identification aims to match a person's identity across multip...
Person re-identification aims at establishing the identity of a pedestri...
The availability of labeled image datasets has been shown critical for
h...
Studies show that refining real-world categories into semantic subcatego...
Labelled image datasets have played a critical role in high-level image
...
Learning based hashing methods have attracted considerable attention due...
Minimization of the L_∞ norm, which can be viewed as approximately
solvi...