# Temporal-Guided Visual Foundation Models for Event-Based Vision

Source: [Temporal-Guided Visual Foundation Models for Event-Based Vision](<https://www.sota2.com/research/paper/6912c2f02828b7cc6937da09>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-11-12T05:03:44.384Z

Authors: Ruihao Xia, Junhong Cai, Luziwei Leng, Liuyi Wang, Chengju Liu, Ran Cheng, Yang Tang, Pan Zhou

Published: 2025-11-09T05:45:25.000Z

## Abstract

Event cameras offer unique advantages for vision tasks in challenging environments, yet processing asynchronous event streams remains an open challenge. While existing methods rely on specialized architectures or resource-intensive training, the potential of leveraging modern Visual Foundation Models (VFMs) pretrained on image data remains under-explored for event-based vision. To address this, we propose Temporal-Guided VFM (TGVFM), a novel framework that integrates VFMs with our temporal context fusion block seamlessly to bridge this gap. Our temporal block introduces three key components: (1) Long-Range Temporal Attention to model global temporal dependencies, (2) Dual Spatiotemporal Attention for multi-scale frame correlation, and (3) Deep Feature Guidance Mechanism to fuse semantic-temporal features. By retraining event-to-video models on real-world data and leveraging transformer-based VFMs, TGVFM preserves spatiotemporal dynamics while harnessing pretrained representations. Experiments demonstrate SoTA performance across semantic segmentation, depth estimation, and object detection, with improvements of 16%, 21%, and 16% over existing methods, respectively. Overall, this work unlocks the cross-modality potential of image-based VFMs for event-based vision with temporal reasoning. Code is available at https://github.com/XiaRho/TGVFM.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2511.06238>)

[PDF](<https://arxiv.org/pdf/2511.06238.pdf>)
