Vision-Language Integration in Multimodal Video Transformers (Partially)
Aligns with the Brain
- URL: http://arxiv.org/abs/2311.07766v1
- Date: Mon, 13 Nov 2023 21:32:37 GMT
- Title: Vision-Language Integration in Multimodal Video Transformers (Partially)
Aligns with the Brain
- Authors: Dota Tianai Dong and Mariya Toneva
- Abstract summary: We present a promising approach for probing a pre-trained multimodal video transformer model by leveraging neuroscientific evidence of multimodal information processing in the brain.
We find evidence that vision enhances masked prediction performance during language processing, providing support that cross-modal representations in models can benefit individual modalities.
We show that the brain alignment of the pre-trained joint representation can be improved by fine-tuning using a task that requires vision-language inferences.
- Score: 5.496000639803771
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Integrating information from multiple modalities is arguably one of the
essential prerequisites for grounding artificial intelligence systems with an
understanding of the real world. Recent advances in video transformers that
jointly learn from vision, text, and sound over time have made some progress
toward this goal, but the degree to which these models integrate information
from modalities still remains unclear. In this work, we present a promising
approach for probing a pre-trained multimodal video transformer model by
leveraging neuroscientific evidence of multimodal information processing in the
brain. Using brain recordings of participants watching a popular TV show, we
analyze the effects of multi-modal connections and interactions in a
pre-trained multi-modal video transformer on the alignment with uni- and
multi-modal brain regions. We find evidence that vision enhances masked
prediction performance during language processing, providing support that
cross-modal representations in models can benefit individual modalities.
However, we don't find evidence of brain-relevant information captured by the
joint multi-modal transformer representations beyond that captured by all of
the individual modalities. We finally show that the brain alignment of the
pre-trained joint representation can be improved by fine-tuning using a task
that requires vision-language inferences. Overall, our results paint an
optimistic picture of the ability of multi-modal transformers to integrate
vision and language in partially brain-relevant ways but also show that
improving the brain alignment of these models may require new approaches.
Related papers
- Multimodal Large Language Models and Tunings: Vision, Language, Sensors, Audio, and Beyond [51.141270065306514]
This tutorial aims to equip researchers, practitioners, and newcomers with the knowledge and skills to leverage multimodal AI.
We will cover the latest multimodal datasets and pretrained models, including those beyond vision and language.
Hands-on laboratories will offer practical experience with state-of-the-art multimodal models.
arXiv Detail & Related papers (2024-10-08T01:41:56Z) - Revealing Vision-Language Integration in the Brain with Multimodal Networks [21.88969136189006]
We use (multi) deep neural networks (DNNs) to probe for sites of multimodal integration in the human brain by predicting stereoencephalography (SEEG) recordings taken while human subjects watched movies.
We operationalize sites of multimodal integration as regions where a multimodal vision-language model predicts recordings better than unimodal language, unimodal vision, or linearly-integrated language-vision models.
arXiv Detail & Related papers (2024-06-20T16:43:22Z) - Towards Multi-Task Multi-Modal Models: A Video Generative Perspective [5.495245220300184]
This thesis chronicles our endeavor to build multi-task models for generating videos and other modalities under diverse conditions.
We unveil a novel approach to mapping bidirectionally between visual observation and interpretable lexical terms.
Our scalable visual token representation proves beneficial across generation, compression, and understanding tasks.
arXiv Detail & Related papers (2024-05-26T23:56:45Z) - Neuro-Vision to Language: Enhancing Brain Recording-based Visual Reconstruction and Language Interaction [8.63068449082585]
Decoding non-invasive brain recordings is pivotal for advancing our understanding of human cognition.
Our framework integrates 3D brain structures with visual semantics using a Vision Transformer 3D.
We have enhanced the fMRI dataset with diverse fMRI-image-related textual data to support multimodal large model development.
arXiv Detail & Related papers (2024-04-30T10:41:23Z) - Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives [56.2139730920855]
We present a systematic analysis of MM-VUFMs specifically designed for road scenes.
Our objective is to provide a comprehensive overview of common practices, referring to task-specific models, unified multi-modal models, unified multi-task models, and foundation model prompting techniques.
We provide insights into key challenges and future trends, such as closed-loop driving systems, interpretability, embodied driving agents, and world models.
arXiv Detail & Related papers (2024-02-05T12:47:09Z) - Multimodal Neurons in Pretrained Text-Only Transformers [52.20828443544296]
We identify "multimodal neurons" that convert visual representations into corresponding text.
We show that multimodal neurons operate on specific visual concepts across inputs, and have a systematic causal effect on image captioning.
arXiv Detail & Related papers (2023-08-03T05:27:12Z) - Brain encoding models based on multimodal transformers can transfer
across language and vision [60.72020004771044]
We used representations from multimodal transformers to train encoding models that can transfer across fMRI responses to stories and movies.
We found that encoding models trained on brain responses to one modality can successfully predict brain responses to the other modality.
arXiv Detail & Related papers (2023-05-20T17:38:44Z) - Multimodal foundation models are better simulators of the human brain [65.10501322822881]
We present a newly-designed multimodal foundation model pre-trained on 15 million image-text pairs.
We find that both visual and lingual encoders trained multimodally are more brain-like compared with unimodal ones.
arXiv Detail & Related papers (2022-08-17T12:36:26Z) - i-Code: An Integrative and Composable Multimodal Learning Framework [99.56065789066027]
i-Code is a self-supervised pretraining framework where users may flexibly combine the modalities of vision, speech, and language into unified and general-purpose vector representations.
The entire system is pretrained end-to-end with new objectives including masked modality unit modeling and cross-modality contrastive learning.
Experimental results demonstrate how i-Code can outperform state-of-the-art techniques on five video understanding tasks and the GLUE NLP benchmark, improving by as much as 11%.
arXiv Detail & Related papers (2022-05-03T23:38:50Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.