Towards zero shot learning of geometry of motion streams and its application to anomaly recognition

摘要

Visual anomaly recognition (VAR) is the core part of many intelligent systems. However, vagueness in definitions and lack of a priori knowledge about the distribution of anomalies make VAR a challenging problem. Supervised solutions often fail to work in such scenarios due to a lack of ability to adapt with concept drifts. To this end, we have studied the effect of temporal derivatives over differential manifolds for designing a zero-shot (label agnostic) VAR solution. The rationale behind this work is leveraging the genericity and discriminative representation available in the geometric-structure of motion-tensors. Our approach proceeds by drawing segments of temporal-derivatives from raw image-sequences and projecting them over Grassmann product space before clustering. Suitability of the proposed approach is corroborated with extensive experiments and comparisons with other arts.