Brain-Aligned Multi-Stream Video Transformers with Sparse Self-Selection

• URL: http://arxiv.org/abs/2607.17625v1
• Date: Mon, 20 Jul 2026 07:30:16 GMT
• Title: Brain-Aligned Multi-Stream Video Transformers with Sparse Self-Selection
• Abstract summary: We introduce a sparse winner-takes-all token selection module to improve efficiency and approximate competitive routing observed in biological visual circuits.<n>We propose a neuro-inspired split-and-fuse video transformer which uses two complementary pathways: a high-resolution, low-frame-rate "what" stream and a low-resolution, high-frame-rate "where" stream.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern video transformers typically ignore principles from primate vision and are rarely evaluated against neural data, limiting their biological interpretability. We introduce a sparse winner-takes-all token selection module that replaces dense self-attention to improve efficiency and approximate competitive routing observed in biological visual circuits. We further propose a neuro-inspired split-and-fuse video transformer which uses two complementary pathways: a high-resolution, low-frame-rate "what" stream and a low-resolution, high-frame-rate "where" stream, fused before classification. On Kinetics-400 and Something-Something V2, our best variant operates on the Pareto frontier of accuracy versus inference time among models of comparable scale and pretraining, and showing improved robustness to spatial perturbations. Using representational similarity analysis between model embeddings and time-resolved EEG recordings for the same video stimuli, our model attains a peak brain-model correlation of 0.18 (about 78% of the noise ceiling) and consistently outperforms strong video transformer baselines, suggesting that pathway specialization and sparse competition are useful inductive biases for efficient, brain-aligned video understanding.

Related papers

• DuoFormer: Leveraging Hierarchical Representations by Local and Global Attention Vision Transformer [1.456352735394398]
  We propose a novel hierarchical transformer model that adeptly integrates the feature extraction capabilities of Convolutional Neural Networks (CNNs) with the advanced representational potential of Vision Transformers (ViTs)<n> Addressing the lack of inductive biases and dependence on extensive training datasets in ViTs, our model employs a CNN backbone to generate hierarchical visual representations.<n>These representations are adapted for transformer input through an innovative patch tokenization process, preserving the inherited multi-scale inductive biases.
  arXiv  Detail & Related papers  (2025-06-15T22:42:57Z)
• FullTransNet: Full Transformer with Local-Global Attention for Video Summarization [16.134118247239527]
  We propose a transformer-like architecture named FullTransNet for video summarization.<n>It uses a full transformer with an encoder-decoder structure as an alternative architecture for video summarization.<n>Our model achieves F-scores of 54.4% and 63.9%, respectively, while maintaining relatively low computational and memory requirements.
  arXiv  Detail & Related papers  (2025-01-01T16:07:27Z)
• DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains [1.5124439914522694]
  DeDiNAT is a deblurring Transformer based on Dilated Neighborhood Attention.<n>A cross-channel learner aids the Transformer block to understand the short-range relationships between adjacent channels.<n>Compared to state-of-the-art models, our compact DeDiNAT demonstrates superior generalization capabilities and achieves remarkable performance in perceptual metrics.
  arXiv  Detail & Related papers  (2024-03-19T21:31:31Z)
• Dynamics Based Neural Encoding with Inter-Intra Region Connectivity [2.3825930751052358]
  We propose the first large-scale study focused on comparing video understanding models with respect to the visual cortex recordings using video stimuli.<n>We provide key insights on how video understanding models predict visual cortex responses.<n>We propose a novel neural encoding scheme that is built on top of the best performing video understanding models.
  arXiv  Detail & Related papers  (2024-02-19T20:29:49Z)
• Large-kernel Attention for Efficient and Robust Brain Lesion Segmentation [0.08694241595813026]
  We propose an all-convolutional transformer block variant of the U-Net architecture. Our model provides the greatest compromise in three factors: performance competitive with the state-of-the-art; parameter efficiency of a CNN; and the favourable inductive biases of a transformer.
  arXiv  Detail & Related papers  (2023-08-14T16:38:13Z)
• Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition [112.66832145320434]
  Video-FocalNet is an effective and efficient architecture for video recognition that models both local global contexts. Video-FocalNet is based on a-temporal focal modulation architecture that reverses the interaction and aggregation steps of self-attention. We show that Video-FocalNets perform favorably well against state-of-the-art transformer-based models for video recognition on five large-scale datasets.
  arXiv  Detail & Related papers  (2023-07-13T17:59:33Z)
• Dual-path Adaptation from Image to Video Transformers [62.056751480114784]
  We efficiently transfer the surpassing representation power of the vision foundation models, such as ViT and Swin, for video understanding with only a few trainable parameters. We propose a novel DualPath adaptation separated into spatial and temporal adaptation paths, where a lightweight bottleneck adapter is employed in each transformer block.
  arXiv  Detail & Related papers  (2023-03-17T09:37:07Z)
• SVFormer: Semi-supervised Video Transformer for Action Recognition [88.52042032347173]
  We introduce SVFormer, which adopts a steady pseudo-labeling framework to cope with unlabeled video samples. In addition, we propose a temporal warping to cover the complex temporal variation in videos. In particular, SVFormer outperforms the state-of-the-art by 31.5% with fewer training epochs under the 1% labeling rate of Kinetics-400.
  arXiv  Detail & Related papers  (2022-11-23T18:58:42Z)
• Error Correction Code Transformer [92.10654749898927]
  We propose to extend for the first time the Transformer architecture to the soft decoding of linear codes at arbitrary block lengths. We encode each channel's output dimension to high dimension for better representation of the bits information to be processed separately. The proposed approach demonstrates the extreme power and flexibility of Transformers and outperforms existing state-of-the-art neural decoders by large margins at a fraction of their time complexity.
  arXiv  Detail & Related papers  (2022-03-27T15:25:58Z)
• Improving Neural Predictivity in the Visual Cortex with Gated Recurrent Connections [0.0]
  We aim to shift the focus on architectures that take into account lateral recurrent connections, a ubiquitous feature of the ventral visual stream, to devise adaptive receptive fields. In order to increase the robustness of our approach and the biological fidelity of the activations, we employ specific data augmentation techniques.
  arXiv  Detail & Related papers  (2022-03-22T17:27:22Z)
• Video Frame Interpolation Transformer [86.20646863821908]
  We propose a Transformer-based video framework that allows content-aware aggregation weights and considers long-range dependencies with the self-attention operations. To avoid the high computational cost of global self-attention, we introduce the concept of local attention into video. In addition, we develop a multi-scale frame scheme to fully realize the potential of Transformers.
  arXiv  Detail & Related papers  (2021-11-27T05:35:10Z)
• Long-Short Temporal Contrastive Learning of Video Transformers [62.71874976426988]
  Self-supervised pretraining of video transformers on video-only datasets can lead to action recognition results on par or better than those obtained with supervised pretraining on large-scale image datasets. Our approach, named Long-Short Temporal Contrastive Learning, enables video transformers to learn an effective clip-level representation by predicting temporal context captured from a longer temporal extent.
  arXiv  Detail & Related papers  (2021-06-17T02:30:26Z)
• Conformer: Convolution-augmented Transformer for Speech Recognition [60.119604551507805]
  Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR) We propose the convolution-augmented transformer for speech recognition, named Conformer. On the widely used LibriSpeech benchmark, our model achieves WER of 2.1%/4.3% without using a language model and 1.9%/3.9% with an external language model on test/testother.
  arXiv  Detail & Related papers  (2020-05-16T20:56:25Z)

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.