This material may not be published, broadcast, rewritten, or redistributed. Quotes displayed in real-time or delayed by at least 15 minutes. Market data provided by Factset . Powered and implemented by FactSet Digital Solutions . Mutual Fund and ETF data provided by Refinitiv Lipper .

Image Captioning for state-of-the-art VLMs has significantly improved over time; however, this comes at the cost of increased computational complexity, making them less accessible for resource-constrained applications such as mobile devices and assistive technologies. Alternatively, smaller VLMs prioritize high-level scene descriptions, overlooking finer details that contribute to a richer understanding of an image. In this paper, we introduce a training-free framework that enhances caption diversity and informativeness by explicitly attending to distinct image regions using a comparably small VLM, BLIP, as the backbone. Our approach leverages structured segmentation to produce hierarchical representations that capture both global and localized semantics. Without requiring additional model training, we demonstrate that our method allows smaller VLMs to achieve performance comparable to larger models in terms of image-caption alignment, semantic integrity, and diversity. We evaluate our framework on MSCOCO, Flickr30k, and Nocaps test datasets, achieving a Div-2 score of 0.735, 0.750, and 0.748 for each dataset respectively, while maintaining strong image-caption relevancy and semantic integrity with the human-annotated captions.

To the average person, it must seem as if the field of artificial intelligence is making immense progress. According to the press releases, and some of the more gushing media accounts, OpenAI's DALL-E 2 can seemingly create spectacular images from any text; another OpenAI system called GPT-3 can talk about just about anything; and a system called Gato that was released in May by DeepMind, a division of Alphabet, seemingly worked well on every task the company could throw at it. One of DeepMind's high-level executives even went so far as to brag that in the quest for artificial general intelligence (AGI), AI that has the flexibility and resourcefulness of human intelligence, "The Game is Over!" And Elon Musk said recently that he would be surprised if we didn't have artificial general intelligence by 2029. Machines may someday be as smart as people, and perhaps even smarter, but the game is far from over.

Major "Star Wars" geeks like to obsess over minutiae, but even the most astute fans probably missed the brief glimpse of Luke Skywalker's iconic surfboard and baseball bat while he was dueling with Kylo Ren in "The Last Jedi." But a neural network spotted them both, revealing comical limitations in today's best AI. Janelle Shane, the artificial intelligence expert who used AI to create bizarre candy hearts and kitten names sicced two pre-existing algorithms called DeepLab and SPADE on the iconic "Star Wars" and watched the chaos unfold. Shane shared the results online and, well, they're unusual. DeepLab interpreted the scene frame-by-frame and segmented the image into different objects.

This tampered image (left) can be detected by noting visual artifacts (red rectangle, showing the unnaturally high contrast along the baseball player's edges), compared to authentic regions (the parking lot background); and by noting noise pattern inconsistencies between the tampered regions and the background (as seen in "Noise" image). The "ground-truth" image is the outline of the added (fake) image used in the experiment. Thanks to user-friendly image editing software like Adobe Photoshop, it's becoming increasingly difficult and time-consuming to spot some deceptive image manipulations. Now, funded by DARPA, researchers at Adobe and the University of Maryland, College Park have turned to AI to detect the more subtle methods now used in doctoring images. What used to take an image-forensic expert several hours to do can now be done in seconds with AI, says Vlad Morariu, PhD, a senior research scientist at Adobe.

Baseball arguably has the deepest game analytics out of any major league sport. These insights are only generated during games using expensive, specialized equipment and a team of expert baseball statisticians. It would be impossible to generate similar statistics in real-time for amateur competition or recreational play. However, one avid baseball fan has built two smartphone applications to allow recreational baseball players to generate these statistics as they practice and play. PASoftware Team (from left to right): Andrew White (CIO), Jacob Zarbosky (CTO), Will Bowen (VP), Matt Bowen (Founder & CEO). Matthew Bowen is the founder of PASoftware, a baseball video analytics software startup brings the power and accuracy of multi-million dollar Major League Baseball analytics systems to your smartphone.

The long fly ball in baseball is a thing of beauty. Spectators hold their breath as the ball arcs gracefully into the sky and then hurtles towards the outfield with a uniformed player in pursuit. Sometimes it ends up nestling gracefully in the hollow of an outstretched glove. When it works, it seems like a simple act, but catching success asks a fascinating question: how do baseball outfielders coordinate their run perfectly to take a long fly ball? The answer reveals something about the way our brains work and gives us an insight into the future of machine learning.

Silicon Valley tech giants and startups alike have for years been trying to drum up excitement around Internet-connected home appliances. But despite the push from companies like Samsung, Google and Apple, consumer adoption has been slow. Only 7% of households in the Americas were estimated to have connected home tech by the end of 2017, according to research from IHS Markit. Shoppers have had good reasons to avoid smart home gadgets. They're usually more expensive than their "dumb" counterparts, they can be complicated to set up and use, and the true utility they offer can be unclear.

The research comes from the Duke University Medical Center. With the study, computer scientists discovered that baseball players with higher scores on computer-based vision and motor tasks went on to have better on-base percentages. In addition, these players had more walks and fewer strikeouts ('plate discipline') compared with those who did not take part in similar tests. Artificial intelligence was used to make the predictions, drawing inferences from Bayesian hierarchical latent variable models. The inference is that the baseball scouts of tomorrow who are on the look out for a consistent, conscientious hitter may find as many clues by assessing data gathered from how the player completes task in front of a computer screen as they would from watching the player exhibit his or her sporting prowess on the field.

Click on the blue word above the attention of the medical profession, every day there are material! When it comes to Dr. Siddartha (Siddhartha Mukherjee), perhaps a lot of people are unfamiliar with his name. But a lot of people are familiar with his two book, "the king of all diseases: cancer," and "genes: Intimate History.". The former allows Dr. Mukherjee to get a non fiction Pulitzer prize, while the latter was recommended as the best book of 2016 by Mr. Bill Gate. Recently, Dr. Mukherjee in "New York guest" (The New Yorker) published a long article, the unique perspective of a doctor, artificial intelligence survey in recent years the impact for medicine. The seven story is he in this long article record, outlines the future doctors and artificial intelligence, harmonious coexistence. The author Dr. Mukherjee is a doctor, but also a good writer. One night in November 2016, a 54 year old woman in New York, Bronx (Bronx) was sent to the emergency room at the Columbia University (Columbia University) medical center because of a severe headache. She told the emergency room doctor that his vision was blurred and his left hand was numb. The doctor arranged for CT. A few months later, on January, one of the 4 radiologists huddled in front of a computer on the third floor of the hospital, the room was dark and windowless, with only the screen light, which seemed to be filtered by the sea. She's training them to read CT. "Once the brain shows death and gray, it's easy to diagnose a stroke," Dr. Lignelli-Dipple said. The key is to diagnose a stroke before most nerve cells die." A stroke is usually caused by a blockage or bleeding of the blood vessel. The radiologist has about 45 minutes of window time so that the doctor can intervene in time to dissolve the clot. "Imagine you're in the emergency room right now," continued Dr. Lignelli-Dipple. "Every minute, a part of the brain dies.