Filters








16,591 Hits in 5.6 sec

Diverse Instance Discovery: Vision-Transformer for Instance-Aware Multi-Label Image Recognition [article]

Yunqing Hu, Xuan Jin, Yin Zhang, Haiwen Hong, Jingfeng Zhang, Feihu Yan, Yuan He, Hui Xue
2022 arXiv   pre-print
Our goal is to leverage ViT's patch tokens and self-attention mechanism to mine rich instances in multi-label images, named diverse instance discovery (DiD).  ...  Previous works on multi-label image recognition (MLIR) usually use CNNs as a starting point for research.  ...  To this end, we propose Diverse instance discovery: Vision-Transformer for instance-aware Multi-label Image Recognition.  ... 
arXiv:2204.10731v1 fatcat:a6xikibuyjg7bl2vikbogaakbm

Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning [article]

Supasorn Suwajanakorn, Noah Snavely, Jonathan Tompson, Mohammad Norouzi
2018 arXiv   pre-print
Given a single image, KeypointNet extracts 3D keypoints that are optimized for a downstream task.  ...  Our model discovers geometrically and semantically consistent keypoints across viewing angles and instances of an object category.  ...  These keypoints will serve as a building block for feature representations based on a sparse set of points, useful for geometric reasoning and pose-aware or pose-invariant object recognition (e.g., [43  ... 
arXiv:1807.03146v2 fatcat:zmmvnpamx5a57dfz2a7bgtqhkm

Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation [article]

Tianfei Zhou, Jianwu Li, Xueyi Li, Ling Shao
2021 arXiv   pre-print
each frame, enabling more accurate object discovery.  ...  This paper addresses the task of unsupervised video multi-object segmentation.  ...  In recent years, image-level instance segmentation has attracted great research interests, which extends semantic segmentation [30, 28, 52, 61] to assign different labels for separate instances of objects  ... 
arXiv:2104.04782v1 fatcat:7qa2244w7rgl5ez26euybjcrlq

Automatic Discovery of Political Meme Genres with Diverse Appearances [article]

William Theisen, Joel Brogan, Pamela Bilo Thomas, Daniel Moreira, Pascal Phoa, Tim Weninger, Walter Scheirer
2020 arXiv   pre-print
In this paper we introduce a scalable automated visual recognition pipeline for discovering political meme genres of diverse appearance.  ...  Results show that this approach can discover new meme genres with visually diverse images that share common stylistic elements, paving the way forward for further work in semantic analysis and content  ...  Figure 14 : A crossover between the dyed finger meme and a meme that shows a number of fingers equal to the spot on the ballot of the candidate for which one was voting.  ... 
arXiv:2001.06122v2 fatcat:sb3w55ovn5dvjaerhqbh3svxcu

Structure Diversity-induced Anchor Graph Fusion for Multi-view Clustering

Xun Lu, Songhe Feng
2022 ACM Transactions on Knowledge Discovery from Data  
To overcome these drawbacks, we propose a novel structural fusion framework to integrate the multi-view anchor graphs for clustering.  ...  The anchor graph structure has been widely used to speed up large-scale multi-view clustering and exhibited promising performance.  ...  vision [2] , pattern recognition [4] and data minimization [40] .  ... 
doi:10.1145/3534931 fatcat:25aztaztnzbc7e23yhul3k36sa

Drug discovery with explainable artificial intelligence

José Jiménez-Luna, Francesca Grisoni, Gisbert Schneider
2020 Nature Machine Intelligence  
V arious concepts of 'artificial intelligence' (AI) have been successfully adopted for computer-assisted drug discovery in the past few years 1-3 .  ...  Given the current pace of AI in drug discovery and related fields, there will be an increased demand for methods that help us understand and interpret the underlying models.  ...  This methodology has successfully been applied in several tasks such as image recognition, text classification and visual question answering 82 . • Counterfactual instance search.  ... 
doi:10.1038/s42256-020-00236-4 fatcat:nlkwpc2jvvhcblmiulbdzzxaiq

Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation

Xipeng Chen, Kwan-Yee Lin, Wentao Liu, Chen Qian, Liang Lin
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
In this work, we propose a geometry-aware 3D representation for the human pose to address this limitation by using multiple views in a simple auto-encoder model at the training stage and only 2D keypoint  ...  Recent studies have shown remarkable advances in 3D human pose estimation from monocular images, with the help of large-scale in-door 3D datasets and sophisticated network architectures.  ...  This task is an active research topic in the computer vision community for serving as a key step for many applications, e.g., action recognition, human-computer interaction, and autonomous * Xipeng Chen  ... 
doi:10.1109/cvpr.2019.01115 dblp:conf/cvpr/ChenLLQL19 fatcat:jmcyrerwbnayvawaaer7zsl6qq

Unsupervised Learning from Videos for Object Discovery in Single Images

Dong Zhao, Baoqing Ding, Yulin Wu, Lei Chen, Hongchao Zhou
2020 Symmetry  
We apply the feed-forward network trained from videos for object discovery in single images, which is different from the previous co-segmentation methods that require videos or collections of images as  ...  object instances from a single image.  ...  , recognition, instance segmentation, etc.  ... 
doi:10.3390/sym13010038 fatcat:ohgmg6gmp5culcppemdmhvv42y

NovelCraft: A Dataset for Novelty Detection and Discovery in Open Worlds [article]

Patrick Feeney
2022 arXiv   pre-print
Our new NovelCraft dataset contains multi-modal episodic data of the images and symbolic world-states seen by an agent completing a pogo-stick assembly task within a video game world.  ...  Results suggest an opportunity for future research: models aware of task-specific costs of different types of mistakes could more effectively detect and adapt to novelty in open worlds.  ...  This approach continues to dominate vision research related to novelty detection: The Open World Vision workshop at CVPR 2021 used repurposed images from ImageNet in their open-set recognition challenge  ... 
arXiv:2206.11736v1 fatcat:drhaq6bvcnahlizbpjyw7liuru

Visual Emotion Analysis via Affective Semantic Concept Discovery

Yunwen Zhu, Yonghua Zhu, Ning Ge, Wenjing Gao, Wenjun Zhang
2022 Scientific Programming  
image emotion recognition.  ...  Capturing the emotions embedded in these social images has always been important yet challenging.  ...  Nevertheless, because of the complexity and diversity of image emotion recognition, a large amount of labelled training data with small noise is required to achieve good performance.  ... 
doi:10.1155/2022/6975490 doaj:22d1411f2825471e957e0db028a95c2d fatcat:v2jnxauo2feglien77updwte7e

Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation [article]

Xipeng Chen, Kwan-Yee Lin, Wentao Liu, Chen Qian, Xiaogang Wang, Liang Lin
2019 arXiv   pre-print
In this work, we propose a geometry-aware 3D representation for the human pose to address this limitation by using multiple views in a simple auto-encoder model at the training stage and only 2D keypoint  ...  Recent studies have shown remarkable advances in 3D human pose estimation from monocular images, with the help of large-scale in-door 3D datasets and sophisticated network architectures.  ...  [43] discovery landmark structure as an intermediate representation for image autoencoding with several constraints.  ... 
arXiv:1903.08839v2 fatcat:mgy72vpyfjepjilklnnijvmpqa

Visual Knowledge Discovery with Artificial Intelligence: Challenges and Future Directions [article]

Boris Kovalerchuk, Răzvan Andonie, Nuno Datia, Kawa Nazemi, Ebad Banissi
2022 arXiv   pre-print
This volume is devoted to the emerging field of Integrated Visual Knowledge Discovery that combines advances in Artificial Intelligence/Machine Learning (AI/ML) and Visualization/Visual Analytics.  ...  In this chapter we aim to present challenges and future directions within the field of Visual Analytics, Visual Knowledge Discovery and AI/ML, and to discuss the role of visualization in visual AI/ML.  ...  Recognition for Non-images by Kovalerchuk, Kalla, and Agarwal.  ... 
arXiv:2205.01296v2 fatcat:s3ygky7tcrg2jaj4ihccyg2lzy

Object Discovery From a Single Unlabeled Image by Mining Frequent Itemset With Multi-scale Features [article]

Runsheng Zhang, Yaping Huang, Mengyang Pu, Jian Zhang, Qingji Guan, Qi Zou, Haibin Ling
2020 arXiv   pre-print
TThe goal of our work is to discover dominant objects in a very general setting where only a single unlabeled image is given.  ...  Her research interests are computer vision and pattern recognition.  ...  Her research interests include pattern recognition, computer vision and target tracking.  ... 
arXiv:1902.09968v3 fatcat:2col2budbjgzjoykscdl632qv4

Theory-Guided Data Science: A New Paradigm for Scientific Discovery from Data

Anuj Karpatne, Gowtham Atluri, James H. Faghmous, Michael Steinbach, Arindam Banerjee, Auroop Ganguly, Shashi Shekhar, Nagiza Samatova, Vipin Kumar
2017 IEEE Transactions on Knowledge and Data Engineering  
The overarching vision of TGDS is to introduce scientific consistency as an essential component for learning generalizable models.  ...  Theory-guided data science (TGDS) is an emerging paradigm that aims to leverage the wealth of scientific knowledge for improving the effectiveness of data science models in enabling scientific discovery  ...  It is possible to build predictive models that use multi-spectral data from satellite images as input features to classify pixels of the image as water or land.  ... 
doi:10.1109/tkde.2017.2720168 fatcat:ijqhkol5hrf3fnxjhthmbce7he

Applications of machine learning in drug discovery and development

Jessica Vamathevan, Dominic Clark, Paul Czodrowski, Ian Dunham, Edgardo Ferran, George Lee, Bin Li, Anant Madabhushi, Parantu Shah, Michaela Spitzer, Shanrong Zhao
2019 Nature reviews. Drug discovery  
Machine learning (ML) approaches provide a set of tools that can improve discovery and decision making for well-specified questions with abundant, high-quality data.  ...  Drug discovery and development pipelines are long, complex and depend on numerous factors.  ...  Papa for helpful comments, M. Segler for contributing to the small-molecule optimization subsection and A. Janowczyk for providing the pathology images in Figure 4 .  ... 
doi:10.1038/s41573-019-0024-5 pmid:30976107 pmcid:PMC6552674 fatcat:4gubtr5kz5fe7khrbtfrre4lhy
« Previous Showing results 1 — 15 out of 16,591 results