English
Related papers

Related papers: FrameDiT: Diffusion Transformer with Matrix Attent…

200 papers

As the development of large-scale Generative AI models evolve beyond text (1D) generation to include image (2D) and video (3D) generation, processing spatial and temporal information presents unique challenges to quality, performance, and…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-05-07 Alicia Golden , Samuel Hsia , Fei Sun , Bilge Acun , Basil Hosmer , Yejin Lee , Zachary DeVito , Jeff Johnson , Gu-Yeon Wei , David Brooks , Carole-Jean Wu

Video try-on stands as a promising area for its tremendous real-world potential. Previous research on video try-on has primarily focused on transferring product clothing images to videos with simple human poses, while performing poorly with…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Jun Zheng , Jing Wang , Fuwei Zhao , Xujie Zhang , Xiaodan Liang

Video motion transfer aims to synthesize videos by generating visual content according to a text prompt while transferring the motion pattern observed in a reference video. Recent methods predominantly use the Diffusion Transformer (DiT)…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Yue Ma , Zhikai Wang , Tianhao Ren , Mingzhe Zheng , Hongyu Liu , Jiayi Guo , Kunyu Feng , Yuxuan Xue , Zixiang Zhao , Konrad Schindler , Qifeng Chen , Linfeng Zhang

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

Video diffusion transformers have achieved remarkable progress in high-quality video generation, but remain computationally expensive due to the quadratic complexity of attention over high-dimensional video sequences. Recent acceleration…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Wenhao Sun , Rong-Cheng Tu , Yifu Ding , Zhao Jin , Jingyi Liao , Shunyu Liu , Dacheng Tao

We conduct an in-depth analysis of attention in video diffusion transformers (VDiTs) and report a number of novel findings. We identify three key properties of attention in VDiTs: Structure, Sparsity, and Sinks. Structure: We observe that…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Yuxin Wen , Jim Wu , Ajay Jain , Tom Goldstein , Ashwinee Panda

Diffusion transformers enable flexible generative modeling for video. However, it is still technically challenging and computationally expensive to generate high-resolution videos with rich semantics and complex motion. Similar to…

Computer Vision and Pattern Recognition · Computer Science 2024-12-16 Xunnong Xu , Mengying Cao

Self-attention has become a defacto choice for capturing global context in various vision applications. However, its quadratic computational complexity with respect to image resolution limits its use in real-time applications, especially…

Computer Vision and Pattern Recognition · Computer Science 2023-07-27 Abdelrahman Shaker , Muhammad Maaz , Hanoona Rasheed , Salman Khan , Ming-Hsuan Yang , Fahad Shahbaz Khan

Self-attention learns pairwise interactions to model long-range dependencies, yielding great improvements for video action recognition. In this paper, we seek a deeper understanding of self-attention for temporal modeling in videos. We…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Bo He , Xitong Yang , Zuxuan Wu , Hao Chen , Ser-Nam Lim , Abhinav Shrivastava

The introduction of Transformer model has led to tremendous advancements in sequence modeling, especially in text domain. However, the use of attention-based models for video understanding is still relatively unexplored. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2021-03-19 Saurabh Sahu , Palash Goyal

This paper is on video recognition using Transformers. Very recent attempts in this area have demonstrated promising results in terms of recognition accuracy, yet they have been also shown to induce, in many cases, significant computational…

Computer Vision and Pattern Recognition · Computer Science 2021-06-14 Adrian Bulat , Juan-Manuel Perez-Rua , Swathikiran Sudhakaran , Brais Martinez , Georgios Tzimiropoulos

Diffusion Transformers (DiT) have emerged as a powerful architecture for image and video generation, offering superior quality and scalability. However, their practical application suffers from inherent dynamic feature instability, leading…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Guanjie Chen , Xinyu Zhao , Yucheng Zhou , Xiaoye Qu , Tianlong Chen , Yu Cheng

DIFF Transformer improves attention allocation by enhancing focus on relevant context while suppressing noise. It introduces a differential attention mechanism that calculates the difference between two independently generated attention…

Machine Learning · Computer Science 2025-12-17 Yueyang Cang , Yuhang Liu , Xiaoteng Zhang , Li Shi , Wenge Que

Achieving ID-preserving text-to-video (T2V) generation remains challenging despite recent advances in diffusion-based models. Existing approaches often fail to capture fine-grained facial dynamics or maintain temporal identity coherence. To…

Computer Vision and Pattern Recognition · Computer Science 2025-08-14 Qi Xie , Yongjia Ma , Donglin Di , Xuehao Gao , Xun Yang

Diffusion models are proficient at generating high-quality images. They are however effective only when operating at the resolution used during training. Inference at a scaled resolution leads to repetitive patterns and structural…

Computer Vision and Pattern Recognition · Computer Science 2024-11-28 Haosen Yang , Adrian Bulat , Isma Hadji , Hai X. Pham , Xiatian Zhu , Georgios Tzimiropoulos , Brais Martinez

Latent-space modeling has been the standard for Diffusion Transformers (DiTs). However, it relies on a two-stage pipeline where the pretrained autoencoder introduces lossy reconstruction, leading to error accumulation while hindering joint…

Computer Vision and Pattern Recognition · Computer Science 2026-04-17 Yongsheng Yu , Wei Xiong , Weili Nie , Yichen Sheng , Shiqiu Liu , Jiebo Luo

Recently, Diffusion Transformers (DiTs) have emerged as a dominant architecture in video generation, surpassing U-Net-based models in terms of performance. However, the enhanced capabilities of DiTs come with significant drawbacks,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Junyi Wu , Zhiteng Li , Zheng Hui , Yulun Zhang , Linghe Kong , Xiaokang Yang

Diffusion Transformers (DiTs) excel at generation, but their global self-attention makes controllable, reference-image-based editing a distinct challenge. Unlike U-Nets, naively injecting local appearance into a DiT can disrupt its holistic…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Shengrong Gu , Ye Wang , Song Wu , Rui Ma , Qian Wang , Lanjun Wang , Zili Yi

The diffusion model has gained popularity in vision applications due to its remarkable generative performance and versatility. However, high storage and computation demands, resulting from the model size and iterative generation, hinder its…

Computer Vision and Pattern Recognition · Computer Science 2023-12-12 Junhyuk So , Jungwon Lee , Daehyun Ahn , Hyungjun Kim , Eunhyeok Park

Existing person video generation methods either lack the flexibility in controlling both the appearance and motion, or fail to preserve detailed appearance and temporal consistency. In this paper, we tackle the problem of motion transfer…

Computer Vision and Pattern Recognition · Computer Science 2019-08-13 Kun Cheng , Hao-Zhi Huang , Chun Yuan , Lingyiqing Zhou , Wei Liu