Prevalent techniques in zero-shot learning do not generalize well to other related problem scenarios. Here, we present a unified approach for conventional zero-shot, generalized zero-shot and few-shot learning problems. Our approach is based on a novel Class Adapting Principal Directions (CAPD) concept that allows multiple embeddings of image features into a semantic space. Given an image, our ...

Fluctuation-dissipation relations, such as Crooks’ Theorem and Jarzynski’s Equality, are powerful tools in quantum and classical nonequilibrium statistical mechanics. We link these relations to a newer approach known as “one-shot statistical mechanics.” Rooted in one-shot information theory, one-shot statistical mechanics concerns statements true of every implementation of a protocol, not only ...

In basketball, every time the offense produces a shot opportunity the player with the ball must decide whether the shot is worth taking. In this article, I explore the question of when a team should shoot and when they should pass up the shot by considering a simple theoretical model of the shot selection process, in which the quality of shot opportunities generated by the offense is assumed to...

In this paper, we developed a technique to detect a special kind of shot, namely establishment shot, which is used to introduce a new scene to the audience or remind the audience of a known environment. The detection of establishment shot aids in various middle-level issues such as analyzing the story units of a movie. An establishment shot is usually realized by using camera motions such as pa...

The attempts of this paper are as follows: clarifying the fundamental differences between the one-shot decision theory which was initially proposed in the paper [16] and other decision theories under uncertainty to highlight that the one-shot decision theory is a scenario-based decision theory instead of a lottery-based one; pointing out the instinct problems in other decision theories to show ...

We present a method for detecting shot boundaries and grouping together shots that were taken from identical camera directions. The technique utilizes methods including spectral clustering and phase correlation to achieve fast and accurate segmentation and grouping. Keywords—Shot Segmentation, Shot Boundary Detection, Shot Grouping, Cut Detection