# Achieving Fine-grained Cross-modal Understanding through Brain-inspired Hierarchical Representation Learning

arXiv: https://arxiv.org/abs/2601.01339 · HTML: https://mlsanity.com/paper/2601.01339/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 31 references that are in the map.
- First posted on arXiv 4 Jan 2026.

## Builds on (most cited first, 19 of 19)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [FILIP: Fine-grained Interactive Language-Image Pre-Training](https://mlsanity.com/paper/2111.07783/) (2021)
- [VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding](https://mlsanity.com/paper/2109.14084/) (2021)
- [Diffusion Autoencoders: Toward a Meaningful and Decodable Representation](https://mlsanity.com/paper/2111.15640/) (2021)
- [Spatiotemporal Contrastive Video Representation Learning](https://mlsanity.com/paper/2008.03800/) (2020)
- [Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors](https://mlsanity.com/paper/2305.18274/) (2023)
- [Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding](https://mlsanity.com/paper/2211.06956/) (2022)
- [TCLR: Temporal Contrastive Learning for Video Representation](https://mlsanity.com/paper/2101.07974/) (2021)
- [Generic decoding of seen and imagined objects using hierarchical visual features](https://mlsanity.com/paper/1510.06479/) (2015)
- [MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data](https://mlsanity.com/paper/2403.11207/) (2024)
- [Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activity](https://mlsanity.com/paper/2305.11675/) (2023)
- [Neural Encoding and Decoding with Deep Learning for Dynamic Natural Vision](https://mlsanity.com/paper/1608.03425/) (2016)
- [NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstruction](https://mlsanity.com/paper/2410.19452/) (2024)
- [Towards Principled Representation Learning from Videos for Reinforcement Learning](https://mlsanity.com/paper/2403.13765/) (2024)
- [AnomalyControl: Learning Cross-modal Semantic Features for Controllable Anomaly Synthesis](https://mlsanity.com/paper/2412.06510/) (2024)
- [LLM4Brain: Training a Large Language Model for Brain Video Understanding](https://mlsanity.com/paper/2409.17987/) (2024)

## Abstract (arXiv)

Understanding neural responses to visual stimuli remains challenging due to the inherent complexity of brain representations and the modality gap between neural data and visual inputs. Existing methods, mainly based on reducing neural decoding to generation tasks or simple correlations, fail to reflect the hierarchical and temporal processes of visual processing in the brain. To address these limitations, we present NeuroAlign, a novel framework for fine-grained fMRI-video alignment inspired by the hierarchical organization of the human visual system. Our framework implements a two-stage mechanism that mirrors biological visual pathways: global semantic understanding through Neural-Temporal Contrastive Learning (NTCL) and fine-grained pattern matching through enhanced vector quantization. NTCL explicitly models temporal dynamics through bidirectional prediction between modalities, while our DynaSyncMM-EMA approach enables dynamic multi-modal fusion with adaptive weighting. Experiments demonstrate that NeuroAlign significantly outperforms existing methods in cross-modal retrieval tasks, establishing a new paradigm for understanding visual cognitive mechanisms.