Abstract: Systems, methods, and computer-readable media are disclosed for determining virtual product placement opportunities in a media content and determining product candidates for virtual insertion into the media content. The product placement system may determine shot segments from the media content and for each shot segment may determine candidate product placement locations. The product placement system may determine contextual information from the shot segments and from the contextual information determine candidate products suitable for the product placement locations. The product placement system may determine total screen time for each product placement opportunity as well as quality of each opportunity. For each product and product placement opportunity, the product placement system may determine an expected revenue and a projected insertion cost.

Abstract: Examples disclosed herein are relevant to systems, methods, and other technology for determining furniture compatibility. For example, graph neural networks (GNNs) that leverage relational information between furniture items in a set may be used as models to predict a compatibility score indicative of visual compatibility of furniture items across the set. In one implementation, the GNN-based model can extend the concept of a siamese network to multiple inputs and branches and use a generalized contrastive loss function. In another implementation, the GNN-based model learns both an edge function and the function that generates the compatibility score. The predicted compatibility score can be used for a variety of purposes, including furniture item recommendations.

Abstract: Examples disclosed herein are relevant to systems, methods, and other technology for determining furniture compatibility. For example, graph neural networks (GNNs) that leverage relational information between furniture items in a set may be used as models to predict a compatibility score indicative of visual compatibility of furniture items across the set. In one implementation, the GNN-based model can extend the concept of a siamese network to multiple inputs and branches and use a generalized contrastive loss function. In another implementation, the GNN-based model learns both an edge function and the function that generates the compatibility score. The predicted compatibility score can be used for a variety of purposes, including furniture item recommendations.