Share Ethiopia's Gobena, Kenya's Olympic champion Jepchirchir win Sydney Marathon on social media Ethiopia's Addisu Gobena and Kenyan world champion Peres Jepchirchir surged to commanding Sydney Marathon wins in the men's and women's races . It was the first victory in a World Marathon Major for 21-year-old Gobena, who came second last year, while Jepchirchir, in Australia on Sunday, added to her previous triumphs in Boston, New York and London. The dominant run shattered the course record by almost one and a half minutes, with last year's winner Hailemaryam Kiros dropping from the pace in the dying stages. "I am very happy," said Gobena, who was a javelin thrower before transitioning to long-distance running, gaining international attention by winning the 2024 Dubai Marathon. "Last year I came second, I learnt from my mistake and I went back home and I worked on my mistake to perform and break the record today." The unstoppable Jepchirchir was in a league of her own, crossing the finish line in front of the Sydney Opera House in 2:18:31, nearly four minutes ahead of fellow Kenyan Irine Cheptai and Ethiopia's Shure Demise Ware.

Follow this section to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Follow this tag to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens.

In this paper, we propose to employ the convolutional neural network (CNN) for the image question answering (QA) task. Our proposed CNN provides an end-to-end framework with convolutional architectures for learning not only the image and question representations, but also their inter-modal interactions to produce the answer. More specifically, our model consists of three CNNs: one image CNN to encode the image content, one sentence CNN to compose the words of the question, and one multimodal convolution layer to learn their joint representation for the classification in the space of candidate answer words. We demonstrate the efficacy of our proposed model on the DAQUAR and COCO-QA datasets, which are two benchmark datasets for image QA, with the performances significantly outperforming the state-of-the-art.