Clayton Mellina

Learn More
We propose a simple and straightforward way of creating powerful image representations via cross-dimensional weighting and aggregation of deep convolutional neural network layer outputs. We first present a generalized framework that encompasses a broad family of approaches and includes cross-dimensional pooling and weighting steps. We then propose specific(More)
We propose a novel hashing-based matching scheme, called Locally Optimized Hashing (LOH), based on a state-of-the-art quantization algorithm that can be used for efficient, large-scale search, recommendation, clustering, and deduplication. We show that matching with LOH only requires set intersections and summations to compute and so is easily implemented(More)
Studies suggest that self-harm users found it easier to discuss self-harm-related thoughts and behaviors using social media than in the physical world. Given the enormous and increasing volume of social media data, on-line self-harm content is likely to be buried rapidly by other normal content. To enable voices of self-harm users to be heard, it is(More)
This paper complements our interactive art installation consisting of a back-projected screen and a depth sensor. As participants stand in front of the projection, their silhouettes create an area of hallucination that changes with their movement. Hallucinations may vary; some are "dreams", transporting the area covered by the silhouette to past or future(More)
We investigate the patterns and evolution of cultural ideas and symbols in media using network analysis techniques. We leverage the TV Tropes wiki of media works, cross-referenced with the widelyrecognized character/situation types (tropes) that these works contain, to construct a bipartite graph representation of 4,616 films and their associated tropes. We(More)
  • 1