Multimodal Event Detection: Current Approaches and Defining the New Playground through LLMs and VLMs

In this paper, we study the challenges of detecting events on social media, where traditional unimodal systems struggle due to the rapid and multimodal nature of data dissemination. We employ a range of models, including unimodal ModernBERT and ConvNeXt-V2, multimodal fusion techniques, and advanced generative models like GPT-4o, and LLaVA. Additionally, we also study the effect of providing multimodal generative models (such as GPT-4o) with a single modality to assess their efficacy. Our results indicate that while multimodal approaches notably outperform unimodal counterparts, generative approaches despite having a large number of parameters, lag behind supervised methods in precision. Furthermore, we also found that they lag behind instruction-tuned models because of their inability to generate event classes correctly. During our error analysis, we discovered that common social media issues such as leet speak, text elongation, etc. are effectively handled by generative approaches but are hard to tackle using supervised approaches.

A Multimodal Fusion Framework for Bridge Defect Detection with Cross-Verification

This paper presents a pilot study introducing a multimodal fusion framework for the detection and analysis of bridge defects, integrating Non-Destructive Evaluation (NDE) techniques with advanced image processing to enable precise structural assessment. By combining data from Impact Echo (IE) and Ultrasonic Surface Waves (USW) methods, this preliminary investigation focuses on identifying defect-prone regions within concrete structures, emphasizing critical indicators such as delamination and debonding. Using geospatial analysis with alpha shapes, fusion of defect points, and unified lane boundaries, the proposed framework consolidates disparate data sources to enhance defect localization and facilitate the identification of overlapping defect regions. Cross-verification with adaptive image processing further validates detected defects by aligning their coordinates with visual data, utilizing advanced contour-based mapping and bounding box techniques for precise defect identification. The experimental results, with an F1 score of 0.83, demonstrate the potential efficacy of the approach in improving defect localization, reducing false positives, and enhancing detection accuracy, which provides a foundation for future research and larger-scale validation. This preliminary exploration establishes the framework as a promising tool for efficient bridge health assessment, with implications for proactive structural monitoring and maintenance.