Gustavo MouraFollow


For images with multiple objects, users don't have an easy way to specify the object within the image that interests them. This makes it difficult for users to express image-search intent. This disclosure describes techniques to enable users to specify the object or part of an image that they want to visually search on by long-pressing the relevant object or part. The coordinates of the long-press are used to identify the closest object and to automatically generate visual search results for it.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.