中文
相关论文

相关论文: Masked Autoencoders for Generic Event Boundary Det…

200 篇论文

Lane detection is crucial for vehicle localization which makes it the foundation for automated driving and many intelligent and advanced driving assistant systems. Available vision-based lane detection methods do not make full use of the…

计算机视觉与模式识别 · 计算机科学 2023-08-14 Ruohan Li , Yongqi Dong

Event cameras asynchronously capture brightness changes with low latency, high temporal resolution, and high dynamic range. However, annotation of event data is a costly and laborious process, which limits the use of deep learning methods…

计算机视觉与模式识别 · 计算机科学 2023-12-27 Simon Klenk , David Bonello , Lukas Koestler , Nikita Araslanov , Daniel Cremers

Masked autoencoding has shown excellent performance on self-supervised video representation learning. Temporal redundancy has led to a high masking ratio and customized masking strategy in VideoMAE. In this paper, we aim to further improve…

计算机视觉与模式识别 · 计算机科学 2023-08-22 Bingkun Huang , Zhiyu Zhao , Guozhen Zhang , Yu Qiao , Limin Wang

Despite the tremendous progress of Masked Autoencoders (MAE) in developing vision tasks such as image and video, exploring MAE in large-scale 3D point clouds remains challenging due to the inherent irregularity. In contrast to previous 3D…

计算机视觉与模式识别 · 计算机科学 2023-03-20 Honghui Yang , Tong He , Jiaheng Liu , Hua Chen , Boxi Wu , Binbin Lin , Xiaofei He , Wanli Ouyang

The accurate segmentation of lesions in whole-body PET/CT imaging is es-sential for tumor characterization, treatment planning, and response assess-ment, yet current manual workflows are labor-intensive and prone to inter-observer…

图像与视频处理 · 电气工程与系统科学 2025-09-04 Moona Mazher , Steven A Niederer , Abdul Qayyum

Generic event boundary detection is an important yet challenging task in video understanding, which aims at detecting the moments where humans naturally perceive event boundaries. The main challenge of this task is perceiving various…

计算机视觉与模式识别 · 计算机科学 2022-04-04 Jiaqi Tang , Zhaoyang Liu , Chen Qian , Wayne Wu , Limin Wang

Masked Autoencoders (MAEs) have emerged as a dominant strategy for self-supervised representation learning in natural images, where models are pre-trained to reconstruct masked patches with a pixel-wise mean squared error (MSE) between…

图像与视频处理 · 电气工程与系统科学 2025-07-16 Chetan Madan , Aarjav Satia , Soumen Basu , Pankaj Gupta , Usha Dutta , Chetan Arora

Unsupervised learning methods have become increasingly important in deep learning due to their demonstrated large utilization of datasets and higher accuracy in computer vision and natural language processing tasks. There is a growing trend…

计算机视觉与模式识别 · 计算机科学 2023-10-18 Guoxin Wang , Qingyuan Wang , Ganesh Neelakanta Iyer , Avishek Nag , Deepu John

Cognitive science has shown that humans perceive videos in terms of events separated by the state changes of dominant subjects. State changes trigger new events and are one of the most useful among the large amount of redundant information…

计算机视觉与模式识别 · 计算机科学 2025-02-04 Yuxuan Wang , Difei Gao , Licheng Yu , Stan Weixian Lei , Matt Feiszli , Mike Zheng Shou

The primary objective of this work is to present an alternative approach aimed at reducing the dependency on labeled data. Our proposed method involves utilizing autoencoder pre-training within a face image recognition task with two step…

计算机视觉与模式识别 · 计算机科学 2024-02-09 Enoch Solomon , Abraham Woubie , Eyael Solomon Emiru

There has been a lot of recent interest in designing neural network models to estimate a distribution from a set of examples. We introduce a simple modification for autoencoder neural networks that yields powerful generative models. Our…

机器学习 · 计算机科学 2015-06-08 Mathieu Germain , Karol Gregor , Iain Murray , Hugo Larochelle

Masked Image Modeling (MIM)-based models, such as SdAE, CAE, GreenMIM, and MixAE, have explored different strategies to enhance the performance of Masked Autoencoders (MAE) by modifying prediction, loss functions, or incorporating…

计算机视觉与模式识别 · 计算机科学 2024-06-26 Srinivasa Rao Nandam , Sara Atito , Zhenhua Feng , Josef Kittler , Muhammad Awais

Sound event detection is a challenging task, especially for scenes with multiple simultaneous events. While event classification methods tend to be fairly accurate, event localization presents additional challenges, especially when large…

音频与语音处理 · 电气工程与系统科学 2018-11-12 Sandeep Kothinti , Keisuke Imoto , Debmalya Chakrabarty , Gregory Sell , Shinji Watanabe , Mounya Elhilali

Deep co-training has recently been proposed as an effective approach for image segmentation when annotated data is scarce. In this paper, we improve existing approaches for semi-supervised segmentation with a self-paced and self-consistent…

计算机视觉与模式识别 · 计算机科学 2021-07-15 Ping Wang , Jizong Peng , Marco Pedersoli , Yuanfeng Zhou , Caiming Zhang , Christian Desrosiers

Masked Autoencoding (MAE) has emerged as an effective approach for pre-training representations across multiple domains. In contrast to discrete tokens in natural languages, the input for image MAE is continuous and subject to additional…

计算机视觉与模式识别 · 计算机科学 2022-10-14 Ronghang Hu , Shoubhik Debnath , Saining Xie , Xinlei Chen

Generic Event Boundary Detection (GEBD) aims to identify moments in videos that humans perceive as event boundaries. This paper proposes a novel method for addressing this task, called Structured Context Learning, which introduces the…

计算机视觉与模式识别 · 计算机科学 2025-12-02 Xin Gu , Congcong Li , Xinyao Wang , Dexiang Hong , Libo Zhang , Tiejian Luo , Longyin Wen , Heng Fan

Our winning entry for the CVPR 2023 Generic Event Boundary Captioning (GEBC) competition is detailed in this paper. Unlike conventional video captioning tasks, GEBC demands that the captioning model possess an understanding of immediate…

计算机视觉与模式识别 · 计算机科学 2025-10-09 Yolo Yunlong Tang , Jinrui Zhang , Xiangchen Wang , Teng Wang , Feng Zheng

Masked image modeling is a promising self-supervised learning method for visual data. It is typically built upon image patches with random masks, which largely ignores the variation of information density between them. The question is: Is…

计算机视觉与模式识别 · 计算机科学 2024-01-09 Haijian Chen , Wendong Zhang , Yunbo Wang , Xiaokang Yang

Masked Autoencoders (MAEs) learn generalizable representations for image, text, audio, video, etc., by reconstructing masked input data from tokens of the visible data. Current MAE approaches for videos rely on random patch, tube, or…

计算机视觉与模式识别 · 计算机科学 2022-11-17 Wele Gedara Chaminda Bandara , Naman Patel , Ali Gholami , Mehdi Nikkhah , Motilal Agrawal , Vishal M. Patel

The last years have witnessed the emergence of a promising self-supervised learning strategy, referred to as masked autoencoding. However, there is a lack of theoretical understanding of how masking matters on graph autoencoders (GAEs). In…

机器学习 · 计算机科学 2023-05-30 Jintang Li , Ruofan Wu , Wangbin Sun , Liang Chen , Sheng Tian , Liang Zhu , Changhua Meng , Zibin Zheng , Weiqiang Wang