They're widely considered some of the most charismatic animals in the ocean. Now, it turns out bottlenose dolphins actually'smile' at each other while surfing, chasing and playfighting, according to a new study. Until now, little has been known about how the species - famed for their intelligence and playfulness - interact during playtime. But experts have finally revealed that these dolphins use the'open mouth' facial expression – comparable to a smile – to communicate during social play. The dolphins almost always use the facial expression when they are in their playmate's field of view, the researchers found, and playmates responded by'smiling' back a third of the time.

Whale sharks can carry up to 300 babies at once--at different fetal stages and from different fathers. Zebra sharks experience "virgin birth." These are but a mere sampling of the decade's most fascinating shark discoveries. Some 500 known species of these toothy fish ply our planet's waters, ranging from bite size to bus size, and scientists are still becoming acquainted with most of them. Since 2000, when scientists discovered shark populations were collapsing around the world, research on sharks has ramped up across many fields of study, from paleontology to neuroscience to biomechanics.

--Powerful generative adversarial networks (GAN) have been developed to automatically synthesize realistic images from text. However, most existing tasks are limited to generating simple images such as flowers from captions. In this work, we extend this problem to the less addressed domain of face generation from fine-grained textual descriptions of face, e.g., "A person has curly hair, oval face, and mustache" . We are motivated by the potential of automated face generation to impact and assist critical tasks such as criminal face reconstruction. Since current datasets for the task are either very small or do not contain captions, we generate captions for images in the CelebA dataset by creating an algorithm to automatically convert a list of attributes to a set of captions. We then model the highly multi-modal problem of text to face generation as learning the conditional distribution of faces (conditioned on text) in same latent space. We utilize the current state-of-the-art GAN (DC-GAN with GAN-CLS loss) for learning conditional multi-modality. The presence of more fine-grained details and variable length of the captions makes the problem easier for a user but more difficult to handle compared to the other text-to-image tasks. We flipped the labels for real and fake images and added noise in discriminator . Generated images for diverse textual descriptions show promising results. In the end, we show how the widely used inceptions score is not a good metric to evaluate the performance of generative models used for synthesizing faces from text. I NTRODUCTION Photographic text-to-face synthesis is a mainstream problem with potential applications in image editing, video games, or for accessibility.