English
Related papers

Related papers: YOSE: You Only Select Essential Tokens for Efficie…

200 papers

Diffusion transformers (DiT) have become the de facto choice for generating high-quality images and videos, largely due to their scalability, which enables the construction of larger models for enhanced performance. However, the increased…

Computer Vision and Pattern Recognition · Computer Science 2024-07-02 Pratheba Selvaraju , Tianyu Ding , Tianyi Chen , Ilya Zharkov , Luming Liang

Diffusion models demonstrate outstanding performance in image generation, but their multi-step inference mechanism requires immense computational cost. Previous works accelerate inference by leveraging layer or token cache techniques to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Haowei Zhu , Ji Liu , Ziqiong Liu , Dong Li , Junhai Yong , Bin Wang , Emad Barsoum

Ensuring robust 3D object detection and localization is crucial for many applications in robotics and autonomous driving. Recent models, however, face difficulties in maintaining high performance when applied to domains with differing…

Video Face Enhancement (VFE) aims to restore high-quality facial regions from degraded video sequences, enabling a wide range of practical applications. Despite substantial progress in the field, current methods that primarily rely on video…

Computer Vision and Pattern Recognition · Computer Science 2025-11-21 Shulian Zhang , Yong Guo , Long Peng , Ziyang Wang , Ye Chen , Wenbo Li , Xiao Zhang , Yulun Zhang , Jian Chen

In this paper, we delve into a new task known as small object editing (SOE), which focuses on text-based image inpainting within a constrained, small-sized area. Despite the remarkable success have been achieved by current image inpainting…

Computer Vision and Pattern Recognition · Computer Science 2025-01-03 Yiming Wu , Qihe Pan , Zhen Zhao , Zicheng Wang , Sifan Long , Ronghua Liang

Visual speech recognition aims to identify the sequence of phonemes from continuous speech. Unlike the traditional approach of using 2D image feature extraction methods to derive features of each video frame separately, this paper proposes…

Computer Vision and Pattern Recognition · Computer Science 2016-09-08 Toni Heidenreich , Michael W. Spratling

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

Can Transformer perform 2D object- and region-level recognition from a pure sequence-to-sequence perspective with minimal knowledge about the 2D spatial structure? To answer this question, we present You Only Look at One Sequence (YOLOS), a…

Computer Vision and Pattern Recognition · Computer Science 2021-10-28 Yuxin Fang , Bencheng Liao , Xinggang Wang , Jiemin Fang , Jiyang Qi , Rui Wu , Jianwei Niu , Wenyu Liu

In this paper, we address the challenge of performing open-vocabulary video instance segmentation (OV-VIS) in real-time. We analyze the computational bottlenecks of state-of-the-art foundation models that performs OV-VIS, and propose a new…

Computer Vision and Pattern Recognition · Computer Science 2024-12-06 Bin Yan , Martin Sundermeyer , David Joseph Tan , Huchuan Lu , Federico Tombari

Diffusion Transformers (DiTs) achieve state-of-the-art results in text-to-image, text-to-video generation, and editing. However, their large model size and the quadratic cost of spatial-temporal attention over multiple denoising steps make…

Machine Learning · Computer Science 2025-09-24 Muhammad Adnan , Nithesh Kurella , Akhil Arunkumar , Prashant J. Nair

An increasing number of autoregressive models, such as MAR, FlowAR, xAR, and Harmon adopt diffusion sampling to improve the quality of image generation. However, this strategy leads to low inference efficiency, because it usually takes 50…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Qinyu Zhao , Jaskirat Singh , Ming Xu , Akshay Asthana , Stephen Gould , Liang Zheng

Diffusion Transformers (DiTs) have demonstrated remarkable scalability and quality in image and video generation, prompting growing interest in extending them to controllable generation and editing tasks. However, compared to the image…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Ruonan Yu , Zhenxiong Tan , Zigeng Chen , Songhua Liu , Xinchao Wang

Video object segmentation (VOS) -- predicting pixel-level regions for objects within each frame of a video -- is particularly challenging in agricultural scenarios, where videos of crops include hundreds of small, dense, and occluded…

Computer Vision and Pattern Recognition · Computer Science 2025-04-17 Keyhan Najafian , Farhad Maleki , Lingling Jin , Ian Stavness

Diffusion Transformers (DiTs) achieve state-of-the-art performance in high-fidelity image and video generation but suffer from expensive inference due to their iterative denoising structure. While prior methods accelerate sampling by…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Dong Liu , Yanxuan Yu , Ben Lengerich , Ying Nian Wu

Recent Diffusion Transformers (DiTs) have shown impressive capabilities in generating high-quality single-modality content, including images, videos, and audio. However, it is still under-explored whether the transformer-based diffuser can…

Computer Vision and Pattern Recognition · Computer Science 2024-06-13 Kai Wang , Shijian Deng , Jing Shi , Dimitrios Hatzinakos , Yapeng Tian

Common users have changed from mere consumers to active producers of multimedia data content. Video editing plays an important role in this scenario, calling for simple segmentation tools that can handle fast-moving and deformable video…

Computer Vision and Pattern Recognition · Computer Science 2016-06-13 Thiago Vallin Spina , Alexandre Xavier Falcão

Generative models, particularly diffusion models, have made significant success in data synthesis across various modalities, including images, videos, and 3D assets. However, current diffusion models are computationally intensive, often…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Yuanzhi Zhu , Hanshu Yan , Huan Yang , Kai Zhang , Junnan Li

Open-vocabulary panoptic segmentation aims to segment and classify everything in diverse scenes across an unbounded vocabulary. Existing methods typically employ two-stage or single-stage framework. The two-stage framework involves cropping…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Hongwei Niu , Jie Hu , Jianghang Lin , Guannan Jiang , Shengchuan Zhang

Vision Transformers (ViT) have emerged as the de-facto choice for numerous industry grade vision solutions. But their inference cost can be prohibitive for many settings, as they compute self-attention in each layer which suffers from…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Rajat Koner , Gagan Jain , Prateek Jain , Volker Tresp , Sujoy Paul

Dataset condensation is a crucial tool for enhancing training efficiency by reducing the size of the training dataset, particularly in on-device scenarios. However, these scenarios have two significant challenges: 1) the varying…

Computer Vision and Pattern Recognition · Computer Science 2023-10-24 Yang He , Lingao Xiao , Joey Tianyi Zhou
‹ Prev 1 8 9 10 Next ›