English
Related papers

Related papers: TIMERIPPLE: Accelerating vDiTs by Understanding th…

200 papers

Video diffusion transformers (DiTs) suffer from prohibitive inference latency due to quadratic attention complexity. Existing sparse attention methods either overlook semantic similarity or fail to adapt to heterogeneous token distributions…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Haoyue Tan , Shengnan Wang , Yulin Qiao , Juncheng Zhang , Youhui Bai , Ping Gong , Zewen Jin , Cheng Li

Self-supervised video representation learning aimed at maximizing similarity between different temporal segments of one video, in order to enforce feature persistence over time. This leads to loss of pertinent information related to…

Computer Vision and Pattern Recognition · Computer Science 2023-05-12 Di Yang , Yaohui Wang , Quan Kong , Antitza Dantcheva , Lorenzo Garattoni , Gianpiero Francesca , Francois Bremond

Transformer-based language models have found many diverse applications requiring them to process sequences of increasing length. For these applications, the causal self-attention -- which is the only component scaling quadratically w.r.t.…

Machine Learning · Computer Science 2023-06-05 Matteo Pagliardini , Daniele Paliotta , Martin Jaggi , François Fleuret

Recent advancements in Diffusion Transformers (DiTs) have established them as the state-of-the-art method for video generation. However, their inherently sequential denoising process results in inevitable latency, limiting real-world…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Hanshuai Cui , Zhiqing Tang , Zhifei Xu , Zhi Yao , Wenyi Zeng , Weijia Jia

Video-language alignment is a crucial multi-modal task that benefits various downstream applications, e.g., video-text retrieval and video question answering. Existing methods either utilize multi-modal information in video-text pairs or…

Computer Vision and Pattern Recognition · Computer Science 2024-07-25 Shi-Xue Zhang , Hongfa Wang , Xiaobin Zhu , Weibo Gu , Tianjin Zhang , Chun Yang , Wei Liu , Xu-Cheng Yin

Diffusion Transformers have demonstrated remarkable performance in video generation. However, their long input sequences incur substantial latency due to the quadratic complexity of full attention. Various sparse attention mechanisms have…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Tongcheng Fang , Hanling Zhang , Ruiqi Xie , Zhuo Han , Xin Tao , Tianchen Zhao , Pengfei Wan , Wenbo Ding , Wanli Ouyang , Xuefei Ning , Yu Wang

Video transformer naturally incurs a heavier computation burden than a static vision transformer, as the former processes $T$ times longer sequence than the latter under the current attention of quadratic complexity $(T^2N^2)$. The existing…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Hao Zhang , Lechao Cheng , Yanbin Hao , Chong-Wah Ngo

Taking inspiration from physical motion, we present a new self-supervised dynamics learning strategy for videos: Video Time-Differentiation for Instance Discrimination (ViDiDi). ViDiDi is a simple and data-efficient strategy, readily…

Computer Vision and Pattern Recognition · Computer Science 2024-09-10 Siyi Chen , Minkyu Choi , Zesen Zhao , Kuan Han , Qing Qu , Zhongming Liu

Image-to-video adaptation seeks to efficiently adapt image models for use in the video domain. Instead of finetuning the entire image backbone, many image-to-video adaptation paradigms use lightweight adapters for temporal modeling on top…

Computer Vision and Pattern Recognition · Computer Science 2024-07-10 Rui Qian , Shuangrui Ding , Dahua Lin

Large Vision-Language Models (VLMs) have achieved remarkable success in multi-modal reasoning, but their inference time efficiency remains a significant challenge due to the memory overhead during decoding, especially when the query and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Fatih Ilhan , Gaowen Liu , Ramana Rao Kompella , Selim Furkan Tekin , Tiansheng Huang , Zachary Yahn , Yichang Xu , Ling Liu

In the era of generative AI, integrating video generation models into robotics opens new possibilities for the general-purpose robot agent. This paper introduces imitation learning with latent video planning (VILP). We propose a latent…

Robotics · Computer Science 2025-02-05 Zhengtong Xu , Qiang Qiu , Yu She

Self-attention has recently been adopted for a wide range of sequence modeling problems. Despite its effectiveness, self-attention suffers from quadratic compute and memory requirements with respect to sequence length. Successful approaches…

Machine Learning · Computer Science 2020-10-27 Aurko Roy , Mohammad Saffar , Ashish Vaswani , David Grangier

Video generation has been advancing rapidly, and diffusion transformer (DiT) based models have demonstrated remark- able capabilities. However, their practical deployment is of- ten hindered by slow inference speeds and high memory con-…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Sijie Wang , Qiang Wang , Shaohuai Shi

Diffusion models with their powerful expressivity and high sample quality have achieved State-Of-The-Art (SOTA) performance in the generative domain. The pioneering Vision Transformer (ViT) has also demonstrated strong modeling capabilities…

Computer Vision and Pattern Recognition · Computer Science 2024-08-30 Ali Hatamizadeh , Jiaming Song , Guilin Liu , Jan Kautz , Arash Vahdat

The Transformer architecture has revolutionized deep learning, delivering the state-of-the-art performance in areas such as natural language processing, computer vision, and time series prediction. However, its core component,…

Machine Learning · Computer Science 2025-07-24 Haolin Jin , Mengbai Xiao , Yuan Yuan , Xiao Zhang , Dongxiao Yu , Guanghui Zhang , Haoliang Wang

Sounding Video Generation (SVG) remains a challenging task due to the inherent structural misalignment between audio and video, as well as the high computational cost of multimodal data processing. In this paper, we introduce ProAV-DiT, a…

Multimedia · Computer Science 2025-11-18 Jiahui Sun , Weining Wang , Mingzhen Sun , Yirong Yang , Xinxin Zhu , Jing Liu

Self-attention has been successfully applied to video representation learning due to the effectiveness of modeling long range dependencies. Existing approaches build the dependencies merely by computing the pairwise correlations along…

Computer Vision and Pattern Recognition · Computer Science 2021-05-28 Xudong Guo , Xun Guo , Yan Lu

Transformer-based methods have recently achieved great advancement on 2D image-based vision tasks. For 3D video-based tasks such as action recognition, however, directly applying spatiotemporal transformers on video data will bring heavy…

Computer Vision and Pattern Recognition · Computer Science 2022-07-28 Wangmeng Xiang , Chao Li , Biao Wang , Xihan Wei , Xian-Sheng Hua , Lei Zhang

Diffusion models have revolutionized video generation, becoming essential tools in creative content generation and physical simulation. Transformer-based architectures (DiTs) and classifier-free guidance (CFG) are two cornerstones of this…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Zhiye Song , Steve Dai , Ben Keller , Brucek Khailany

We present STCDiT, a video super-resolution framework built upon a pre-trained video diffusion model, aiming to restore structurally faithful and temporally stable videos from degraded inputs, even under complex camera motions. The main…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Junyang Chen , Jiangxin Dong , Long Sun , Yixin Yang , Jinshan Pan