English
Related papers

Related papers: PERF-Net: Pose Empowered RGB-Flow Net

200 papers

We present a feed-forward human performance capture method that renders novel views of a performer from a monocular RGB stream. A key challenge in this setting is the lack of sufficient observations, especially for unseen regions. Assuming…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Youngjoong Kwon , Yao He , Heejung Choi , Chen Geng , Zhengmao Liu , Jiajun Wu , Ehsan Adeli

We propose a novel ConvNet model for predicting 2D human body poses in an image. The model regresses a heatmap representation for each body keypoint, and is able to learn and represent both the part appearances and the context of the part…

Computer Vision and Pattern Recognition · Computer Science 2017-08-08 Vasileios Belagiannis , Andrew Zisserman

In this paper, we present a method for real-time multi-person human pose estimation from video by utilizing convolutional neural networks. Our method is aimed for use case specific applications, where good accuracy is essential and…

Computer Vision and Pattern Recognition · Computer Science 2016-09-26 Marko Linna , Juho Kannala , Esa Rahtu

We introduce StreamDiffusion, a real-time diffusion pipeline designed for interactive image generation. Existing diffusion models are adept at creating images from text or image prompts, yet they often fall short in real-time interaction.…

Computer Vision and Pattern Recognition · Computer Science 2025-07-09 Akio Kodaira , Chenfeng Xu , Toshiki Hazama , Takanori Yoshimoto , Kohei Ohno , Shogo Mitsuhori , Soichi Sugano , Hanying Cho , Zhijian Liu , Masayoshi Tomizuka , Kurt Keutzer

Existing methods in video action recognition mostly do not distinguish human body from the environment and easily overfit the scenes and objects. In this work, we present a conceptually simple, general and high-performance framework for…

Computer Vision and Pattern Recognition · Computer Science 2018-12-18 Jiagang Zhu , Wei Zou , Liang Xu , Yiming Hu , Zheng Zhu , Manyu Chang , Junjie Huang , Guan Huang , Dalong Du

We bring together ideas from recent work on feature design for egocentric action recognition under one framework by exploring the use of deep convolutional neural networks (CNN). Recent work has shown that features such as hand appearance,…

Computer Vision and Pattern Recognition · Computer Science 2016-05-13 Minghuang Ma , Haoqi Fan , Kris M. Kitani

Existing methods for video-based person re-identification (ReID) mainly learn the appearance feature of a given pedestrian via a feature extractor and a feature aggregator. However, the appearance models would fail when different…

Computer Vision and Pattern Recognition · Computer Science 2022-09-26 Honghu Pan , Qiao Liu , Yongyong Chen , Yunqi He , Yuan Zheng , Feng Zheng , Zhenyu He

Recognising human activities from streaming videos poses unique challenges to learning algorithms: predictive models need to be scalable, incrementally trainable, and must remain bounded in size even when the data stream is arbitrarily…

Machine Learning · Statistics 2016-10-06 Rocco De Rosa , Ilaria Gori , Fabio Cuzzolin , Barbara Caputo , Nicolò Cesa-Bianchi

Pose-Guided Person Image Synthesis (PGPIS) generates realistic person images conditioned on a target pose and a source image. This task plays a key role in various real-world applications, such as sign language video generation, AR/VR,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-07 Jiwoo Jeong , Kirok Kim , Wooju Kim , Nam-Joon Kim

Recently, diffusion models have shown their impressive ability in visual generation tasks. Besides static images, more and more research attentions have been drawn to the generation of realistic videos. The video generation not only has a…

Computer Vision and Pattern Recognition · Computer Science 2025-11-03 Yucheng Xing , Jinxing Yin , Xiaodong Liu

For the two-stream style methods in action recognition, fusing the two streams' predictions is always by the weighted averaging scheme. This fusion method with fixed weights lacks of pertinence to different action videos and always needs…

Computer Vision and Pattern Recognition · Computer Science 2017-09-14 Jiagang Zhu , Wei Zou , Zheng Zhu

Image manipulation detection is different from traditional semantic object detection because it pays more attention to tampering artifacts than to image content, which suggests that richer features need to be learned. We propose a…

Computer Vision and Pattern Recognition · Computer Science 2018-05-15 Peng Zhou , Xintong Han , Vlad I. Morariu , Larry S. Davis

The convolution neural nets (conv nets) have achieved a state-of-the-art performance in many applications of image and video processing. The most recent studies illustrate that the conv nets are fragile in terms of recognition accuracy to…

Computer Vision and Pattern Recognition · Computer Science 2019-10-25 Sergey Tarasenko , Fumihiko Takahashi

Action segmentation is a challenging yet active research area that involves identifying when and where specific actions occur in continuous video streams. Most existing work has focused on single-stream approaches that model the…

Computer Vision and Pattern Recognition · Computer Science 2025-10-10 Harshala Gammulle , Clinton Fookes , Sridha Sridharan , Simon Denman

We present a new pose transfer method for synthesizing a human animation from a single image of a person controlled by a sequence of body poses. Existing pose transfer methods exhibit significant visual artifacts when applying to a novel…

Computer Vision and Pattern Recognition · Computer Science 2021-11-23 Jae Shin Yoon , Lingjie Liu , Vladislav Golyanik , Kripasindhu Sarkar , Hyun Soo Park , Christian Theobalt

In this paper, we propose a convolutional layer inspired by optical flow algorithms to learn motion representations. Our representation flow layer is a fully-differentiable layer designed to capture the `flow' of any representation channel…

Computer Vision and Pattern Recognition · Computer Science 2019-08-05 AJ Piergiovanni , Michael S. Ryoo

Video frame prediction remains a fundamental challenge in computer vision with direct implications for autonomous systems, video compression, and media synthesis. We present FG-DFPN, a novel architecture that harnesses the synergy between…

Image and Video Processing · Electrical Eng. & Systems 2025-03-17 M. Akın Yılmaz , Ahmet Bilican , A. Murat Tekalp

We present a novel approach for the task of human pose transfer, which aims at synthesizing a new image of a person from an input image of that person and a target pose. We address the issues of limited correspondences identified between…

Computer Vision and Pattern Recognition · Computer Science 2019-03-28 Yining Li , Chen Huang , Chen Change Loy

In this paper, a new network-transmission-based (NTB) algorithm is proposed for human activity recognition in videos. The proposed NTB algorithm models the entire scene as an error-free network. In this network, each node corresponds to a…

Computer Vision and Pattern Recognition · Computer Science 2015-02-24 Weiyao Lin , Yuanzhe Chen , Jianxin Wu , Hanli Wang , Bin Sheng , Hongxiang Li

Two-stream networks have been very successful for solving the problem of action detection. However, prior work using two-stream networks train both streams separately, which prevents the network from exploiting regularities between the two…

Computer Vision and Pattern Recognition · Computer Science 2018-02-26 Alaaeldin El-Nouby , Graham W. Taylor