Girish Kulkarni

Learn More
We develop and demonstrate automatic image description methods using a large captioned photo collection. One contribution is our technique for the automatic collection of this new dataset – performing a huge number of Flickr queries and then filtering the noisy results down to 1 million images with associated visually relevant captions. Such a collection(More)
We posit that visually descriptive language offers computer vision researchers both information about the world, and information about how people describe the world. The potential benefit from this source is made more significant due to the enormous amount of language data easily available today. We present a system to automatically generate natural(More)
We present a system to automatically generate natural language descriptions from images. This system consists of two parts. The first part, content planning, smooths the output of computer vision-based detection and recognition algorithms with statistics mined from large pools of visually descriptive text to determine the best content words to use to(More)
Studying natural language, and especially how people describe the world around them can help us better understand the visual world. In turn, it can also help us in the quest to generate natural language that describes this world in a human manner. We present a simple yet effective approach to automatically compose image descriptions given computer vision(More)
BACKGROUND Studies of complications resulting from surgery or radiotherapy for prostate cancer have mainly focused on incontinence and erectile dysfunction. We aimed to assess other important complications associated with these treatments for prostate cancer. METHODS We did a population-based retrospective cohort study, in which we used administrative(More)
BACKGROUND Brachytherapy, active surveillance, and watchful waiting are increasingly being offered to men with low-risk prostate cancer. However, many of these men harbor undetected high-grade disease (Gleason pattern > or =4). The ability to identify those individuals with occult high-grade disease may help guide treatment decisions in this patient cohort.(More)
CONTEXT High-grade T1 (formerly T1G3) bladder cancer (BCa) has a high propensity to recur and progress. As a result, decisions pertaining to its treatment are difficult. Treatment with bacillus Calmette-Guérin (BCG) risks progression and metastases but may preserve the bladder. Cystectomy may offer the best opportunity for cure but is associated with(More)
BACKGROUND An elevated neutrophil-to-lymphocyte ratio (NLR) is associated with poor outcome in various tumours. Its prognostic utility in patients with urothelial carcinoma of the bladder (UCB) undergoing radical cystectomy (RC) is yet to be fully elucidated. METHODS A cohort of patients undergoing RC for UCB in a tertiary referral centre between 1992 and(More)
PURPOSE To evaluate the association between cumulative duration of metformin use after prostate cancer (PC) diagnosis and all-cause and PC-specific mortality among patients with diabetes. PATIENTS AND METHODS We used a population-based retrospective cohort design. Data were obtained from several Ontario health care administrative databases. Within a(More)
UNLABELLED What's known on the subject? and What does the study add? Elderly patients have more years to compound comorbidities and it has previously been shown that comorbidity is an important predictor of overall survival in patients with bladder cancer, including those treated with radical cystectomy (RC). Other studies have also demonstrated higher(More)