Learn More
We propose NEIL (Never Ending Image Learner), a computer program that runs 24 hours per day and 7 days per week to automatically extract visual knowledge from Internet data. NEIL uses a semi-supervised learning algorithm that jointly discovers common sense relationships (e.g., "Corolla is a kind of/looks similar to Car", "Wheel is a part of Car") and labels(More)
The goal of this work is to find <i>visually similar</i> images even if they appear quite different at the raw pixel level. This task is particularly important for matching images across visual domains, such as photos taken over different seasons or lighting conditions, paintings, hand-drawn sketches, etc. We propose a surprisingly simple method that(More)
The field of object detection has made significant advances riding on the wave of region-based ConvNets, but their training procedure still includes many heuristics and hyperparameters that are costly to tune. We present a simple yet surprisingly effective online hard example mining (OHEM) algorithm for training region-based ConvNet detectors. Our(More)
In recent years, we have seen tremendous progress in the field of object detection. Most of the recent improvements have been achieved by targeting deeper feedforward networks. However, many hard object categories, such as bottle and remote, require representation of fine details and not coarse, semantic representations. But most of these fine details are(More)
There have been some recent efforts to build visual knowledge bases from Internet images. But most of these approaches have focused on bounding box representation of objects. In this paper, we propose to enrich these knowledge bases by automatically discovering objects and their segmentations from noisy Internet images. Specifically, our approach combines(More)
L-asparaginase catalyzes the hydrolysis of L-asparagine into aspartate and ammonia, which is used as an anti-neoplastic agent. Isolation of asparaginase from microorganisms may be cardinal for producing this anticancer agent at industrial level. A total of three hundred fungal isolates were screened for L-asparaginase production. These fungal isolates were(More)
We consider the problem of semi-supervised bootstrap learning for scene categorization. Existing semi-supervised approaches are typically unreliable and face semantic drift because the learning task is under-constrained. This is primarily because they ignore the strong interactions that often exist between scene categories, such as the common attributes(More)
L-Asparaginase (EC3.5.1.1) is an enzyme, which is used for treatment of acute lymphoblastic leukaemia (ALL) and other related blood cancers from a long time. This enzyme selectively hydrolyzes the extracellular amino acid L-asparagine into L-aspartate and ammonia, leading to nutritional deficiencies, protein synthesis inhibition, and ultimately death of(More)
L-Asparaginase is an enzyme used in the treatment of acute lymphoblastic leukemia and other related malignancies. Its further use includes reduction of asparagine concentration in food products, which may lead to formation of acrylamide. Currently bacterial asparaginase is produced at industrial scale, but the enzyme isolated from bacterial origin is often(More)
This paper proposes a novel part-based representation for modeling object categories. Our representation combines the effectiveness of deformable part-based models with the richness of geometric representation by defining parts based on consistent underlying 3D geometry. Our key hypothesis is that while the appearance and the arrangement of parts might vary(More)