visual sense
Mammals can dream and can make 'visual sense' of the world before they're born
Researchers at Yale University have discovered that mammals have the ability to dream and make'visual sense' of the world before they've even opened their eyes for the first time. The new study looked at waves of activity in neonatal retinas of a group of mice that had not yet opened their eyes for the first time and found that they are'capable of pretty sophisticated behavior.' The retinal waves moved in a pattern similar to what would be seen if the animal was actually moving in a physical environment. 'This early dream-like activity makes evolutionary sense because it allows a mouse to anticipate what it will experience after opening its eyes, and be prepared to respond immediately to environmental threats,' the study's co-author Yale School of Medicine professor Michael Crair said in a statement. Yale researchers have discovered mammals dream before they've opened their eyes for the first time.
Discovering and Distinguishing Multiple Visual Senses for Polysemous Words
Yao, Yazhou (University of Technology Sydney) | Zhang, Jian (University of Technology Sydney) | Shen, Fumin (University of Electronic Science and Technology of China) | Yang, Wankou (Southeast University) | Huang, Pu (Nanjing University of Posts and Telecommunications) | Tang, Zhenmin (Nanjing University of Science and Technology)
To reduce the dependence on labeled data, there have been increasing research efforts on learning visual classifiers by exploiting web images. One issue that limits their performance is the problem of polysemy. To solve this problem, in this work, we present a novel framework that solves the problem of polysemy by allowing sense-specific diversity in search results. Specifically, we first discover a list of possible semantic senses to retrieve sense-specific images. Then we merge visual similar semantic senses and prune noises by using the retrieved images. Finally, we train a visual classifier for each selected semantic sense and use the learned sense-specific classifiers to distinguish multiple visual senses. Extensive experiments on classifying images into sense-specific categories and re-ranking search results demonstrate the superiority of our proposed approach.