The recently proposed ImageNet dataset consists of several million images, each annotated with a single object category. However, these annotations may be imperfect, in the sense t...
Active learning strategies can be useful when manual labeling
effort is scarce, as they select the most informative
examples to be annotated first. However, for visual category
...
Sudheendra Vijayanarasimhan (University of Texas a...
We address the problem of weakly supervised semantic segmentation. The training images are labeled only by the classes they contain, not by their location in the image. On test im...
Alexander Vezhnevets, Vittorio Ferrari, Joachim M....
In this paper, we present a novel localized Markov random field (MRF) method based on superpixels for region segmentation. Early vision problems could be formulated as pixel label...
Extracting information from web pages is an important problem; it has several applications such as providing improved search results and construction of databases to serve user qu...
Paramveer S. Dhillon, Sundararajan Sellamanickam, ...