English
Related papers

Related papers: MM-ViT: Multi-Modal Video Transformer for Compress…

200 papers

In this work, we present a novel approach for motion customization in video generation, addressing the widespread gap in the exploration of motion representation within video generative models. Recognizing the unique challenges posed by the…

Computer Vision and Pattern Recognition · Computer Science 2024-10-18 Luozhou Wang , Ziyang Mai , Guibao Shen , Yixun Liang , Xin Tao , Pengfei Wan , Di Zhang , Yijun Li , Yingcong Chen

Recently, the Transformer module has been transplanted from natural language processing to computer vision. This paper applies the Transformer to video-based person re-identification, where the key issue is to extract the discriminative…

Computer Vision and Pattern Recognition · Computer Science 2021-03-31 Tianyu Zhang , Longhui Wei , Lingxi Xie , Zijie Zhuang , Yongfei Zhang , Bo Li , Qi Tian

We present Multiscale Vision Transformers (MViT) for video and image recognition, by connecting the seminal idea of multiscale feature hierarchies with transformer models. Multiscale Transformers have several channel-resolution scale…

Computer Vision and Pattern Recognition · Computer Science 2021-04-23 Haoqi Fan , Bo Xiong , Karttikeya Mangalam , Yanghao Li , Zhicheng Yan , Jitendra Malik , Christoph Feichtenhofer

Previous works on multi-label image recognition (MLIR) usually use CNNs as a starting point for research. In this paper, we take pure Vision Transformer (ViT) as the research base and make full use of the advantages of Transformer with…

Computer Vision and Pattern Recognition · Computer Science 2022-04-25 Yunqing Hu , Xuan Jin , Yin Zhang , Haiwen Hong , Jingfeng Zhang , Feihu Yan , Yuan He , Hui Xue

Automatic video activity recognition is crucial across numerous domains like surveillance, healthcare, and robotics. However, recognizing human activities from video data becomes challenging when training and test data stem from diverse…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Partho Ghosh , Raisa Bentay Hossain , Mohammad Zunaed , Taufiq Hasan

Vision Transformers (ViTs) achieve state-of-the-art segmentation accuracy but require large training datasets because each layer has unique parameters that must be learned independently. We present RD-ViT, a Recurrent-Depth Vision…

Computer Vision and Pattern Recognition · Computer Science 2026-05-06 Renjie He

Video understanding usually requires expensive computation that prohibits its deployment, yet videos contain significant spatiotemporal redundancy that can be exploited. In particular, operating directly on the motion vectors and residuals…

Computer Vision and Pattern Recognition · Computer Science 2020-04-23 Barak Battash , Haim Barad , Hanlin Tang , Amit Bleiweiss

Recent video inpainting methods have made remarkable progress by utilizing explicit guidance, such as optical flow, to propagate cross-frame pixels. However, there are cases where cross-frame recurrence of the masked video is not available,…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Yongsheng Yu , Heng Fan , Libo Zhang

Transformer-based diffusion models have recently superseded traditional U-Net architectures, with multimodal diffusion transformers (MM-DiT) emerging as the dominant approach in state-of-the-art models like Stable Diffusion 3 and Flux.1.…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Joonghyuk Shin , Alchan Hwang , Yujin Kim , Daneul Kim , Jaesik Park

Recent advances on Vision Transformer (ViT) and its improved variants have shown that self-attention-based networks surpass traditional Convolutional Neural Networks (CNNs) in most vision tasks. However, existing ViTs focus on the standard…

Computer Vision and Pattern Recognition · Computer Science 2022-05-24 Xiaofeng Mao , Gege Qi , Yuefeng Chen , Xiaodan Li , Ranjie Duan , Shaokai Ye , Yuan He , Hui Xue

Conventionally, spatiotemporal modeling network and its complexity are the two most concentrated research topics in video action recognition. Existing state-of-the-art methods have achieved excellent accuracy regardless of the complexity…

Computer Vision and Pattern Recognition · Computer Science 2021-01-06 Wenhao Wu , Dongliang He , Tianwei Lin , Fu Li , Chuang Gan , Errui Ding

Action recognition in videos has attracted a lot of attention in the past decade. In order to learn robust models, previous methods usually assume videos are trimmed as short sequences and require ground-truth annotations of each video…

Computer Vision and Pattern Recognition · Computer Science 2019-02-21 Xiao-Yu Zhang , Haichao Shi , Changsheng Li , Kai Zheng , Xiaobin Zhu , Lixin Duan

Single-modality tracking (RGB-only) struggles under low illumination, weather, and occlusion. Multimodal tracking addresses this by combining complementary cues. While Vision Transformer-based trackers achieve strong accuracy, they are…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Mahdi Falaki , Maria A. Amer

We propose global context vision transformer (GC ViT), a novel architecture that enhances parameter and compute utilization for computer vision. Our method leverages global context self-attention modules, joint with standard local…

Computer Vision and Pattern Recognition · Computer Science 2023-06-07 Ali Hatamizadeh , Hongxu Yin , Greg Heinrich , Jan Kautz , Pavlo Molchanov

Action recognition in videos poses a challenge due to its high computational cost, especially for Joint Space-Time video transformers (Joint VT). Despite their effectiveness, the excessive number of tokens in such architectures…

Computer Vision and Pattern Recognition · Computer Science 2024-01-11 Qian Wu , Ruoxuan Cui , Yuke Li , Haoqi Zhu

Diverse input data modalities can provide complementary cues for several tasks, usually leading to more robust algorithms and better performance. However, while a (training) dataset could be accurately designed to include a variety of…

Computer Vision and Pattern Recognition · Computer Science 2018-10-30 Nuno Garcia , Pietro Morerio , Vittorio Murino

Low-light image enhancement (LLIE) is a fundamental yet challenging task due to the presence of noise, loss of detail, and poor contrast in images captured under insufficient lighting conditions. Recent methods often rely solely on…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Alexandru Brateanu , Raul Balmez , Ciprian Orhei , Codruta Ancuti , Cosmin Ancuti

In this paper a pure-attention bottom-up approach, called ViGAT, that utilizes an object detector together with a Vision Transformer (ViT) backbone network to derive object and frame features, and a head network to process these features…

Computer Vision and Pattern Recognition · Computer Science 2022-11-01 Nikolaos Gkalelis , Dimitrios Daskalakis , Vasileios Mezaris

Learning-based video compression has been extensively studied over the past years, but it still has limitations in adapting to various motion patterns and entropy models. In this paper, we propose multi-mode video compression (MMVC), a…

Image and Video Processing · Electrical Eng. & Systems 2023-04-06 Bowen Liu , Yu Chen , Rakesh Chowdary Machineni , Shiyu Liu , Hun-Seok Kim

Recently, several Vision Transformer (ViT) based methods have been proposed for Fine-Grained Visual Classification (FGVC).These methods significantly surpass existing CNN-based ones, demonstrating the effectiveness of ViT in FGVC…

Computer Vision and Pattern Recognition · Computer Science 2022-03-25 Zi-Chao Zhang , Zhen-Duo Chen , Yongxin Wang , Xin Luo , Xin-Shun Xu