Cefdet: Cognitive Effectiveness Network Based on Fuzzy Inference for Action Detection

TL;DR

A cognitive effectiveness network based on fuzzy inference (Cefdet) is proposed, which introduces the concept of 'cognition--based detection' to simulate human cognition to solve the problem of detection effectiveness.

Abstract

Action detection and understanding provide the foundation for the generation and interaction of multimedia content. However, existing methods mainly focus on constructing complex relational inference networks, overlooking the judgment of detection effectiveness. Moreover, these methods frequently generate detection results with cognitive abnormalities. To solve the above problems, this study proposes a cognitive effectiveness network based on fuzzy inference (Cefdet), which introduces the concept of "cognition-based detection" to simulate human cognition. First, a fuzzy-driven cognitive effectiveness evaluation module (FCM) is established to introduce fuzzy inference into action detection. FCM is combined with human action features to simulate the cognition-based detection process, which clearly locates the position of frames with cognitive abnormalities. Then, a fuzzy cognitive update strategy (FCS) is proposed based on the FCM, which utilizes fuzzy logic to re-detect the cognition-based detection results and effectively update the results with cognitive abnormalities. Experimental results demonstrate that Cefdet exhibits superior performance against several mainstream algorithms on the public datasets, validating its effectiveness and superiority. Code is available at https://github.com/12sakura/Cefdet.

Figures (6)

• Figure 1: Detection results with cognitive abnormalities in three consecutive frames. (a) is the false detection result of existing methods in highly similar actions, and (b) denotes the detection results of existing methods that do not conform to human action norms.
• Figure 2: The overall framework of Cefdet for action detection. The left module is the Fuzzy--driven cognitive effectiveness evaluation module, abbreviated as FCM, and on the right is the Fuzzy cognitive update strategy, termed FCS.
• Figure 3: The correlation between different actions. The correlations between all actions are normalized to be between [-1, 1], with darker colors indicating lower correlations.
• Figure 4: The position score of frames in action sequences. In a complete action sequence, the closer to the center the frame is, the more reliable it is.
• Figure 5: Illustration of the FCM, which consists of four components: feature quantification, fuzzification, fuzzy inference and defuzzification.