NeuralVisionNet: a probabilistic neural process model for continuous visual anticipation

Read full text Summarise with VIRAT
Authors: Han He, Ruinan Chen, Yixiang Wang, Xia Chen
Cited by: 0
References: 25

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The ability to anticipate future events continuously is a hallmark of biological vision, yet standard deep learning models often struggle with long-term coherence due to the rigid discretization of time. In this paper, we propose NeuralVisionNet, a probabilistic framework that models visual anticipation as a continuous generative process, drawing inspiration from the predictive coding mechanisms of the hippocampal-entorhinal circuit. Our architecture synergizes hierarchical Video Swin Transformers with Attentive Neural Processes, employing a novel grid-like coding scheme to represent spatiotemporal dynamics as a continuous function rather than a fixed sequence of frames. Furthermore, we introduce a variational global latent variable to encode the "event gist," ensuring semantic consistency over extended horizons. Extensive evaluations on KTH, Human 3.6M, and UCF 101 benchmarks demonstrate that NeuralVisionNet significantly outperforms state-of-the-art stochastic baselines in perceptual quality (FVD) and structural fidelity (SSIM), offering a robust computational proof-of-concept for continuous, bio-inspired visual forecasting.

Fields of Study & Subjects

Generative Adversarial Networks and Image Synthesis Visual Attention and Saliency Detection Advanced Image Processing Techniques

Publication details

Journal / source
Frontiers in Computational Neuroscience
Volume
20
Pages
1781080–1781080
Publication date
24 March 2026
Language
EN