Semantic-Aware Frame-Event Fusion based Pattern Recognition via Large Vision-Language Models

TL;DR

This paper introduces SAFE, a novel pattern recognition framework that leverages large-scale vision-language models to fuse RGB frames, event streams, and semantic labels, improving accuracy in event-based pattern recognition tasks.

Contribution

The study proposes a new multimodal fusion framework using pre-trained CLIP models and Transformer networks to effectively integrate visual and semantic information for pattern recognition.

Findings

Outperforms existing methods on HARDVS and PokerEvent datasets.

Effectively integrates semantic labels with visual data using large-scale models.

Demonstrates significant improvement in recognition accuracy.

Abstract

Pattern recognition through the fusion of RGB frames and Event streams has emerged as a novel research area in recent years. Current methods typically employ backbone networks to individually extract the features of RGB frames and event streams, and subsequently fuse these features for pattern recognition. However, we posit that these methods may suffer from key issues like sematic gaps and small-scale backbone networks. In this study, we introduce a novel pattern recognition framework that consolidates the semantic labels, RGB frames, and event streams, leveraging pre-trained large-scale vision-language models. Specifically, given the input RGB frames, event streams, and all the predefined semantic labels, we employ a pre-trained large-scale vision model (CLIP vision encoder) to extract the RGB and event features. To handle the semantic labels, we initially convert them into language descriptions through prompt engineering, and then obtain the semantic features using the pre-trained large-scale language model (CLIP text encoder). Subsequently, we integrate the RGB/Event features and semantic features using multimodal Transformer networks. The resulting frame and event tokens are further amplified using self-attention layers. Concurrently, we propose to enhance the interactions between text tokens and RGB/Event tokens via cross-attention. Finally, we consolidate all three modalities using self-attention and feed-forward layers for recognition. Comprehensive experiments on the HARDVS and PokerEvent datasets fully substantiate the efficacy of our proposed SAFE model. The source code will be made available at https://github.com/Event-AHU/SAFE_LargeVLM.