Abstract. We propose a novel unsupervised transfer learning framework that utilises unlabelled auxiliary data to quantify and select the most relevant transferrable knowledge for r...
The visual world demonstrates organized spatial patterns,
among objects or regions in a scene, object-parts
in an object, and low-level features in object-parts. These
classes o...
Devi Parikh (Carnegie Mellon University), C. Lawre...
Labeling video data is an essential prerequisite for many vision applications that depend on training data, such as visual information retrieval, object recognition, and human act...
As computer vision research considers more object categories and greater variation within object categories, it is clear that larger and more exhaustive datasets are necessary. How...
Brendan Collins, Jia Deng, Kai Li, Fei-Fei Li 0002
Recent work shows how to use local spatio-temporal features to learn models of realistic human actions from video. However, existing methods typically rely on a predefined spatial...