English
Related papers

Related papers: UltraViCo: Breaking Extrapolation Limits in Video …

200 papers

Vision transformer has achieved impressive performance for many vision tasks. However, it may suffer from high redundancy in capturing local features for shallow layers. Local self-attention or early-stage convolutions are thus utilized,…

Computer Vision and Pattern Recognition · Computer Science 2024-01-26 Huaibo Huang , Xiaoqiang Zhou , Jie Cao , Ran He , Tieniu Tan

The advent of Vision Transformers (ViTs) marks a substantial paradigm shift in the realm of computer vision. ViTs capture the global information of images through self-attention modules, which perform dot product computations among…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Shuoxi Zhang , Hanpeng Liu , Stephen Lin , Kun He

Diffusion transformers (DiTs) have emerged as a dominant architecture for text-to-image generation, yet their performance drops when generating at resolutions beyond their training range. Existing training-free approaches mitigate this by…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Javad Rajabi , Kimia Shaban , Koorosh Roohi , David B. Lindell , Babak Taati

Event cameras excel at high-speed, low-power, and high-dynamic-range scene perception. However, as they fundamentally record only relative intensity changes rather than absolute intensity, the resulting data streams suffer from a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Gang Xu , Zhiyu Zhu , Junhui Hou

Infrared and visible image fusion integrates information from distinct spectral bands to enhance image quality by leveraging the strengths and mitigating the limitations of each modality. Existing approaches typically treat image fusion and…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Jinyuan Liu , Bowei Zhang , Qingyun Mei , Xingyuan Li , Yang Zou , Zhiying Jiang , Long Ma , Risheng Liu , Xin Fan

Long-sequence video diffusion transformers hit a quadratic self-attention cost that dominates runtime and memory for very long token sequences. Most efficient attention methods use one approximation everywhere, yet video features are…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Haopeng Jin

Video object segmentation is a fundamental research problem in computer vision. Recent techniques have often applied attention mechanism to object representation learning from video sequences. However, due to temporal changes in the video…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Quang-Trung Truong , Duc Thanh Nguyen , Binh-Son Hua , Sai-Kit Yeung

Unified multimodal models hold the promise of generating extensive, interleaved narratives, weaving text and imagery into coherent long-form stories. However, current systems suffer from a critical reliability gap: as sequences grow,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Haoyu Chen , Qing Liu , Yuqian Zhou , He Zhang , Zhaowen Wang , Mengwei Ren , Jingjing Ren , Xiang Wang , Zhe Lin , Lei Zhu

Since the introduction of the transformer model by Vaswani et al. (2017), a fundamental question has yet to be answered: how does a model achieve extrapolation at inference time for sequences that are longer than it saw during training? We…

Computation and Language · Computer Science 2022-04-26 Ofir Press , Noah A. Smith , Mike Lewis

In this study, we identify the inefficient attention phenomena in Large Vision-Language Models (LVLMs), notably within prominent models like LLaVA-1.5, QwenVL-Chat and Video-LLaVA. We find out that the attention computation over visual…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Liang Chen , Haozhe Zhao , Tianyu Liu , Shuai Bai , Junyang Lin , Chang Zhou , Baobao Chang

Existing works on video frame interpolation (VFI) mostly employ deep neural networks that are trained by minimizing the L1, L2, or deep feature space distance (e.g. VGG loss) between their outputs and ground-truth frames. However, recent…

Image and Video Processing · Electrical Eng. & Systems 2024-06-11 Duolikun Danier , Fan Zhang , David Bull

We present a convolution-free approach to video classification built exclusively on self-attention over space and time. Our method, named "TimeSformer," adapts the standard Transformer architecture to video by enabling spatiotemporal…

Computer Vision and Pattern Recognition · Computer Science 2021-06-10 Gedas Bertasius , Heng Wang , Lorenzo Torresani

Collecting multi-view driving scenario videos to enhance the performance of 3D visual perception tasks presents significant challenges and incurs substantial costs, making generative models for realistic data an appealing alternative. Yet,…

Computer Vision and Pattern Recognition · Computer Science 2025-04-29 Junpeng Jiang , Gangyi Hong , Miao Zhang , Hengtong Hu , Kun Zhan , Rui Shao , Liqiang Nie

Recently, learning based video compression methods attract increasing attention. However, the previous works suffer from error propagation due to the accumulation of reconstructed error in inter predictive coding. Meanwhile, the previous…

Image and Video Processing · Electrical Eng. & Systems 2020-03-26 Guo Lu , Chunlei Cai , Xiaoyun Zhang , Li Chen , Wanli Ouyang , Dong Xu , Zhiyong Gao

Length Generalization is the essential capacity of autonomous agents to perform tasks in longer contexts than those encountered during training. To systematically study this feat, we test how well models can approximate the next token…

The key to video inpainting is to use correlation information from as many reference frames as possible. Existing flow-based propagation methods split the video synthesis process into multiple steps: flow completion -> pixel propagation ->…

Computer Vision and Pattern Recognition · Computer Science 2022-07-22 Jaeyeon Kang , Seoung Wug Oh , Seon Joo Kim

Low-light image enhancement aims to improve the visibility of degraded images to better align with human visual perception. While diffusion-based methods have shown promising performance due to their strong generative capabilities. However,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-25 Jinhong He , Minglong Xue , Zhipu Liu , Mingliang Zhou , Aoxiang Ning , Palaiahnakote Shivakumara

Video generation has achieved remarkable progress with the introduction of diffusion models, which have significantly improved the quality of generated videos. However, recent research has primarily focused on scaling up model training,…

Computer Vision and Pattern Recognition · Computer Science 2025-01-16 Chenyang Si , Weichen Fan , Zhengyao Lv , Ziqi Huang , Yu Qiao , Ziwei Liu

Visuomotor imitation learning policies enable robots to efficiently acquire manipulation skills from visual demonstrations. However, as scene complexity and visual distractions increase, policies that perform well in simple settings often…

Artificial Intelligence · Computer Science 2025-11-11 Yuhang Dong , Haizhou Ge , Yupei Zeng , Jiangning Zhang , Beiwen Tian , Hongrui Zhu , Yufei Jia , Ruixiang Wang , Zhucun Xue , Guyue Zhou , Longhua Ma , Guanzhong Tian

Video diffusion models have advanced rapidly in the recent years as a result of series of architectural innovations (e.g., diffusion transformers) and use of novel training objectives (e.g., flow matching). In contrast, less attention has…

Computer Vision and Pattern Recognition · Computer Science 2025-09-12 Dohun Lee , Hyeonho Jeong , Jiwook Kim , Duygu Ceylan , Jong Chul Ye