Abhinav Shrivastava

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 In-ternet 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(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)
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)
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)
OBJECTIVE The goal of this study was to evaluate the background and the clinical profile of nonepileptic seizures (NESs) confirmed by short-term video encephalography (ST-VEEG) recording in an Indian population. METHODS Seventy-one patients with NESs were enrolled. A complete history was taken and the recorded event was reviewed to define the ictal(More)
The availability of large labeled image datasets [1, 2] has been one of the key factors for advances in recognition. These datasets have not only helped boost performance, but have also fostered the development of new techniques. However, compared to images, videos seem like a more natural source of training data because of the additional temporal(More)
Multi-task learning in Convolutional Networks has displayed remarkable success in the field of recognition. This success can be largely attributed to learning shared representations from multiple supervisory tasks. However, existing multi-task approaches rely on enumerating multiple network architectures specific to the tasks at hand, that do not(More)