Finding any Waldo: zero-shot invariant and efficient visual search

arXiv.org Artificial Intelligence

Searching for a target object in a cluttered scene constitutes a fundamental challenge in daily vision. Visual search must be selective enough to discriminate the target from distractors, invariant to changes in the appearance of the target, efficient to avoid exhaustive exploration of the image, and must generalize to locate novel target objects with zero-shot training. Previous work has focused on searching for perfect matches of a target after extensive category-specific training. Here we show for the first time that humans can efficiently and invariantly search for natural objects in complex scenes. To gain insight into the mechanisms that guide visual search, we propose a biologically inspired computational model that can locate targets without exhaustive sampling and generalize to novel objects. The model provides an approximation to the mechanisms integrating bottom-up and top-down signals during search in natural scenes.


Collins' Exit Prompts GOP Scramble, Ballot Questions

U.S. News

Republican leaders from the eight counties in Collins' western New York district will soon meet to discuss the party's next steps following Collins' announcement that he would get out of the race. He was charged last week with illegally using inside information about a biotech company to help his son avoid hundreds of thousands of dollars in loses when one of the company's drugs failed in a medical trial. Collins has pleaded not guilty and vowed to fight the charges.


Different but Equal: Comparing User Collaboration with Digital Personal Assistants vs. Teams of Expert Agents

arXiv.org Artificial Intelligence

This work compares user collaboration with conversational personal assistants vs. teams of expert chatbots. Two studies were performed to investigate whether each approach affects accomplishment of tasks and collaboration costs. Participants interacted with two equivalent financial advice chatbot systems, one composed of a single conversational adviser and the other based on a team of four experts chatbots. Results indicated that users had different forms of experiences but were equally able to achieve their goals. Contrary to the expected, there were evidences that in the teamwork situation that users were more able to predict agent behavior better and did not have an overhead to maintain common ground, indicating similar collaboration costs. The results point towards the feasibility of either of the two approaches for user collaboration with conversational agents.


Turkey's Ince Concedes Defeat in 'Unjust' Race, Warns of One-Man Rule

U.S. News

Ince said he accepted the election results, noting there was no significant difference between the official figures and those collated by his own party. The CHP and international rights groups have complained about what they see as unequal campaign conditions in Turkey.


Trump Commision on Election Integrity Found No Evidence of Voter Fraud

U.S. News

Trump himself said his select Advisory Commission on Election Integrity -- vice-chaired by voter-fraud hard-liner Kris Kobach, Kansas' secretary of state -- had found evidence of widespread voter fraud in records it collected from about 20 states. That's despite multiple academic and independent studies showing the problem of illegal voting is miniscule at worst.