Cewu Lu*, Ranjay Krishna*, Michael Bernstein, Li Fei-Fei
Even though all the images contain the same objects (a person and a bicycle), it is the relationship between the objects that determine the holistic interpretation of the image.
Visual relationships capture a wide variety of interactions between pairs of objects in images (e.g. “man riding bicycle” and “man pushing bicycle”). Consequently, the set of possible relationships is extremely large and it is difficult to obtain sufficient training examples for all possible relationships. Because of this limitation, previous work on visual relationship detection has concentrated on predicting only a handful of relationships. Though most relationships are infrequent, their objects (e.g. “man” and “bicycle”) and predicates (e.g. “riding” and “pushing”) independently occur more frequently. We propose a model that uses this insight to train visual models for objects and predicates individually and later combines them together to predict multiple relationships per image. We improve on prior work by leveraging language priors from semantic word embeddings to finetune the likelihood of a predicted relationship. Our model can scale to predict thousands of types of relationships from a few examples. Additionally, we localize the objects in the predicted relationships as bounding boxes in the image. We further demonstrate that understanding relationships can improve content based image retrieval.
The research was published in IEEE European Conference on Computer Vision on 10/27/2016. The research is supported by the Brown Institute Magic Grant for the project Visual Genome.
Access the paper: https://cs.stanford.edu/people/ranjaykrishna/vrd/vrd.pdf
To contact the authors, please send a message to firstname.lastname@example.org