English
Related papers

Related papers: SWAT: Spatial Structure Within and Among Tokens

200 papers

Position emission tomography (PET) is widely used in clinics and research due to its quantitative merits and high sensitivity, but suffers from low signal-to-noise ratio (SNR). Recently convolutional neural networks (CNNs) have been widely…

Image and Video Processing · Electrical Eng. & Systems 2023-12-12 Se-In Jang , Tinsu Pan , Ye Li , Pedram Heidari , Junyu Chen , Quanzheng Li , Kuang Gong

In this paper we propose augmenting Vision Transformer models with learnable memory tokens. Our approach allows the model to adapt to new tasks, using few parameters, while optionally preserving its capabilities on previously learned tasks.…

Computer Vision and Pattern Recognition · Computer Science 2022-03-31 Mark Sandler , Andrey Zhmoginov , Max Vladymyrov , Andrew Jackson

Vision transformers (ViTs) process input images as sequences of patches via self-attention; a radically different architecture than convolutional neural networks (CNNs). This makes it interesting to study the adversarial feature space of…

Computer Vision and Pattern Recognition · Computer Science 2022-03-04 Muzammal Naseer , Kanchana Ranasinghe , Salman Khan , Fahad Shahbaz Khan , Fatih Porikli

Recent advances in multimodal models highlight the pivotal role of image tokenization in high-resolution image generation. By compressing images into compact latent representations, tokenizers enable generative models to operate in…

Computer Vision and Pattern Recognition · Computer Science 2025-12-19 Qihang Rao , Borui Zhang , Wenzhao Zheng , Jie Zhou , Jiwen Lu

The ability to quickly recognize and learn new visual concepts from limited samples enables humans to swiftly adapt to new environments. This ability is enabled by semantic associations of novel concepts with those that have already been…

Computer Vision and Pattern Recognition · Computer Science 2019-09-04 Zitian Chen , Yanwei Fu , Yinda Zhang , Yu-Gang Jiang , Xiangyang Xue , Leonid Sigal

This study aims to address the problem of incomplete information in unimodal images for semantic segmentation and object detection tasks. Existing multimodal fusion methods suffer from limited capability in discriminative modeling of…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Yuchan Jie , Yushen Xu , Xiaosong Li , Huafeng Li , Haishu Tan , Feiping Nie

Self-attention mechanisms, especially multi-head self-attention (MSA), have achieved great success in many fields such as computer vision and natural language processing. However, many existing vision transformer (ViT) works simply inherent…

Computer Vision and Pattern Recognition · Computer Science 2022-11-17 Leijie Wu , Song Guo , Yaohong Ding , Junxiao Wang , Wenchao Xu , Richard Yida Xu , Jie Zhang

Large Language Models (LLMs) are trained to support an increasing number of languages, yet their predefined tokenizers remain a bottleneck for adapting models to lower-resource or distinct-script languages. Existing tokenizer transfer…

Computation and Language · Computer Science 2026-05-12 Mykola Haltiuk , Aleksander Smywinski-Pohl

Vision Transformers achieved outstanding performance in many computer vision tasks. Early Vision Transformers such as ViT and DeiT adopt global self-attention, which is computationally expensive when the number of patches is large. To…

Computer Vision and Pattern Recognition · Computer Science 2022-10-20 Tan Yu , Gangming Zhao , Ping Li , Yizhou Yu

Numerous embedding models have been recently explored to incorporate semantic knowledge into visual recognition. Existing methods typically focus on minimizing the distance between the corresponding images and texts in the embedding space…

Computer Vision and Pattern Recognition · Computer Science 2017-06-06 Dong Li , Hsin-Ying Lee , Jia-Bin Huang , Shengjin Wang , Ming-Hsuan Yang

Recent advances of incorporating layout information, typically bounding box coordinates, into pre-trained language models have achieved significant performance in entity recognition from document images. Using coordinates can easily model…

Computation and Language · Computer Science 2024-02-26 Prashant Krishnan , Zilong Wang , Yangkun Wang , Jingbo Shang

Tokenizer, serving as a translator to map the intricate visual data into a compact latent space, lies at the core of visual generative models. Based on the finding that existing tokenizers are tailored to image or video inputs, this paper…

Computer Vision and Pattern Recognition · Computer Science 2024-06-14 Junke Wang , Yi Jiang , Zehuan Yuan , Binyue Peng , Zuxuan Wu , Yu-Gang Jiang

Transformer becomes more popular in the vision domain in recent years so there is a need for finding an effective way to interpret the Transformer model by visualizing it. In recent work, Chefer et al. can visualize the Transformer on…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Hoang C. Nguyen , Haeil Lee , Junmo Kim

3D perception of object shapes from RGB image input is fundamental towards semantic scene understanding, grounding image-based perception in our spatially 3-dimensional real-world environments. To achieve a mapping between image views of…

Computer Vision and Pattern Recognition · Computer Science 2021-08-24 Weicheng Kuo , Anelia Angelova , Tsung-Yi Lin , Angela Dai

Image tokenizers play a central role in modern generative models, where the structure of the latent space critically determines the downstream generation performance. A key but underexplored property of effective latent representations is…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Jinsung Lee , Jaemin Oh , Namhun Kim , Dongwon Kim , Byung-Jun Yoon , Suha Kwak

Transformer is a new kind of neural architecture which encodes the input data as powerful features via the attention mechanism. Basically, the visual transformers first divide the input images into several local patches and then calculate…

Computer Vision and Pattern Recognition · Computer Science 2021-10-27 Kai Han , An Xiao , Enhua Wu , Jianyuan Guo , Chunjing Xu , Yunhe Wang

Recent work has shown the potential of transformers for computer vision applications. An image is first partitioned into patches, which are then used as input tokens for the attention mechanism. Due to the expensive quadratic cost of the…

Computer Vision and Pattern Recognition · Computer Science 2021-12-23 Shelly Sheynin , Sagie Benaim , Adam Polyak , Lior Wolf

Effective and Efficient spatio-temporal modeling is essential for action recognition. Existing methods suffer from the trade-off between model performance and model complexity. In this paper, we present a novel Spatio-Temporal Hybrid…

Computer Vision and Pattern Recognition · Computer Science 2020-03-19 Xu Li , Jingwen Wang , Lin Ma , Kaihao Zhang , Fengzong Lian , Zhanhui Kang , Jinjun Wang

Recent work on encoder-decoder models for sequence-to-sequence mapping has shown that integrating both temporal and spatial attention mechanisms into neural networks increases the performance of the system substantially. In this work, we…

Machine Learning · Computer Science 2017-08-04 Stefan Braun , Daniel Neil , Enea Ceolini , Jithendar Anumula , Shih-Chii Liu

In recent years, many video tasks have achieved breakthroughs by utilizing the vision transformer and establishing spatial-temporal decoupling for feature extraction. Although multi-view 3D reconstruction also faces multiple images as…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Zhenwei Zhu , Liying Yang , Ning Li , Chaohao Jiang , Yanyan Liang