Beyond Real versus Fake Towards Intent-Aware Video Analysis
This addresses the societal and security risks of deepfakes by enabling intent-aware video analysis, representing a novel paradigm shift rather than an incremental improvement.
The paper tackles the problem of analyzing manipulated videos by shifting from authenticity detection to understanding intent, introducing the IntentHQ benchmark with 5168 videos annotated into 23 categories and developing a multi-modality model for intent recognition.
The rapid advancement of generative models has led to increasingly realistic deepfake videos, posing significant societal and security risks. While existing detection methods focus on distinguishing real from fake videos, such approaches fail to address a fundamental question: What is the intent behind a manipulated video? Towards addressing this question, we introduce IntentHQ: a new benchmark for human-centered intent analysis, shifting the paradigm from authenticity verification to contextual understanding of videos. IntentHQ consists of 5168 videos that have been meticulously collected and annotated with 23 fine-grained intent-categories, including "Financial fraud", "Indirect marketing", "Political propaganda", as well as "Fear mongering". We perform intent recognition with supervised and self-supervised multi-modality models that integrate spatio-temporal video features, audio processing, and text analysis to infer underlying motivations and goals behind videos. Our proposed model is streamlined to differentiate between a wide range of intent-categories.