Internet Archive Scholar
Filters
























9,525 Hits in 5.2 sec

Towards Interpretable and Robust Hand Detection via Pixel-wise Prediction

Dan Liu, Libo Zhang, Tiejian Luo, Lili Tao, Yanjun Wu
2020 Pattern Recognition  

Preserved Fulltext

Web Archive Capture PDF (4.5 MB)
https://web.archive.org/web/20200321041159/https://arxiv.org/pdf/2001.04163v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:

2020 pre-print arXiv:2001.04163v1 fatcat:fgr4e7m5kfg4hdowave5qnyqs4
The lack of interpretability of existing CNN-based hand detection methods makes it difficult to understand the rationale behind their predictions.  ...  The main improvements include: (1) Detect hands at pixel level to explain what pixels are the basis for its decision and improve transparency of the model. (2) The explainable Highlight Feature Fusion  ...  To the best of our knowledge, this is the first study towards interpretable hand detection. The pixel-wise prediction shows the basis of detection and provides the model interpretability.  ... 
doi:10.1016/j.patcog.2020.107202 fatcat:nk2vwyp63vhjtlhkouksat3xam
Multiple Versions
Citation

Dan Liu, Libo Zhang, Tiejian Luo, Lili Tao, Yanjun Wu. "Towards Interpretable and Robust Hand Detection via Pixel-wise Prediction." Pattern Recognition (2020) 107202

Robust Facial Landmark Detection via a Fully-Convolutional Local-Global Context Network

Daniel Merget, Matthias Rock, Gerhard Rigoll
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (3.0 MB)
https://web.archive.org/web/20200319003600/http://openaccess.thecvf.com/content_cvpr_2018/papers/Merget_Robust_Facial_Landmark_CVPR_2018_paper.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

The kernel convolution is crucial for the convergence of the network because it smoothens the gradients and reduces overfitting.  ...  Our experiments demonstrate the effectiveness of our approach, outperforming several state-of-the-art methods in facial landmark detection.  ...  The heatmap outputs are then scaled up to the original resolution and combined via a pixel-wise hard maximum. Local Figure 6 . Best viewed in the digital version.  ... 
doi:10.1109/cvpr.2018.00088 dblp:conf/cvpr/MergetRR18 fatcat:txttqdcblncxzidh6uu64ywwsq
Citation

Daniel Merget, Matthias Rock, Gerhard Rigoll. "Robust Facial Landmark Detection via a Fully-Convolutional Local-Global Context Network." 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (2018) 781-790

Grid Screener: A Tool for Automated High-throughput Screening on Biochemical and Biological Analysis Platforms

Marcel P. Schilling, Svenja Schmelzer, Joaquin Eduardo Urrutia Gomez, Anna A. Popova, Pavel A. Levkin, Markus Reischl
2021 IEEE Access  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (13.1 MB)
https://web.archive.org/web/20211222092256/https://ieeexplore.ieee.org/ielx7/6287639/6514899/09650903.pdf?tp=&arnumber=9650903&isnumber=6514899&ref=

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

The combination with a robust parameter estimation algorithm lowers the requirements of the detection quality and thus enhances robustness.  ...  In this paper, we introduce a generic method to automatically detect grid structures in images and to perform flexible spot-wise analysis after successful grid detection.  ...  The pixel-wise spot information of predicted segments in terms of ỹ is interpreted and centroid locations of all detected spots are obtained.  ... 
doi:10.1109/access.2021.3135709 fatcat:sbpav73c4nesbbrim5fdlttlqu
DOAJ
Citation

Marcel P. Schilling, Svenja Schmelzer, Joaquin Eduardo Urrutia Gomez, Anna A. Popova, Pavel A. Levkin, Markus Reischl. "Grid Screener: A Tool for Automated High-throughput Screening on Biochemical and Biological Analysis Platforms." IEEE Access (2021) 1-1

Multi-scale Bushfire Detection from Multi-modal Streams of Remote Sensing Data

Thanh Cong Phan, Thanh Tam Nguyen, Thanh Dat Hoang, Quoc Viet Hung Nguyen, Jun Jo
2020 IEEE Access  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (17.3 MB)
https://web.archive.org/web/20210715071354/https://research-repository.griffith.edu.au/bitstream/handle/10072/402241/Phan457156-Published.pdf;jsessionid=97F16632FBC0D3A10E3FA834D13C3AA1?sequence=2

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

It is also robust to the effects of cloud and night-time.  ...  In this paper, we propose a multi-scale deep neural network model that combines both satellite images and weather data for detecting and locating bushfires at both image and pixel level.  ...  ACKNOWLEDGMENT This research is funded by Vietnam National Foundation for Science and Technology Development (NAFOSTED) under grant number 102.01-2019.323.  ... 
doi:10.1109/access.2020.3046649 fatcat:pcoyokt6xnaanpphah3vsy7vye
DOAJ
Citation

Thanh Cong Phan, Thanh Tam Nguyen, Thanh Dat Hoang, Quoc Viet Hung Nguyen, Jun Jo. "Multi-scale Bushfire Detection from Multi-modal Streams of Remote Sensing Data." IEEE Access (2020) 1-1

Retina U-Net: Embarrassingly Simple Exploitation of Segmentation Supervision for Medical Object Detection [article]

Paul F. Jaeger, Simon A. A. Kohl, Sebastian Bickelhaupt, Fabian Isensee, Tristan Anselm Kuder, Heinz-Peter Schlemmer, Klaus H. Maier-Hein
2018 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.4 MB)
https://web.archive.org/web/20200907031601/https://arxiv.org/pdf/1811.08661v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

State-of-the-art object detectors on the other hand, allow for individual object scoring in an end-to-end fashion, while ironically trading in the ability to exploit the full pixel-wise supervision signal  ...  This approach, however, only indirectly solves the coarse localization task by predicting pixel-level scores, requiring ad-hoc heuristics when mapping back to object-level scores.  ...  The applicability of computer aided detection systems in clinical environments however, among other requirements, hinges on their interpretability and robustness, which intuitively decreases with model  ... 
arXiv:1811.08661v1 fatcat:5qwhyq6i7fdp7j2etbgazakpl4
Citation

Paul F. Jaeger, Simon A. A. Kohl, Sebastian Bickelhaupt, Fabian Isensee, Tristan Anselm Kuder, Heinz-Peter Schlemmer, Klaus H. Maier-Hein. "Retina U-Net: Embarrassingly Simple Exploitation of Segmentation Supervision for Medical Object Detection." arXiv (2018)

TOWARDS DETECTING FLOATING OBJECTS ON A GLOBAL SCALE WITH LEARNED SPATIAL FEATURES USING SENTINEL 2

J. Mifdal, N. Longépé, M. Rußwurm
2021 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (6.7 MB)
https://web.archive.org/web/20210618092952/https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/V-3-2021/285/2021/isprs-annals-V-3-2021-285-2021.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

Our experiments demonstrate that harnessing the spatial patterns learned with a CNN is advantageous over pixel-wise classifications that use hand-crafted features.  ...  In contrast to previous work that focuses on pixel-wise spectral responses of some bands, we employ a deep learning predictor that learns the spatial characteristics of floating objects.  ...  Quantitative Comparison to Pixel-Wise Classifiers In Table 1 , we compare the U-Net model with the pixel-wise machine learning classifiers.  ... 
doi:10.5194/isprs-annals-v-3-2021-285-2021 fatcat:437ed3xxhrgyzbgspk2ztwqlg4
DOAJ
Citation

J. Mifdal, N. Longépé, M. Rußwurm. "TOWARDS DETECTING FLOATING OBJECTS ON A GLOBAL SCALE WITH LEARNED SPATIAL FEATURES USING SENTINEL 2." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences (2021) 285-293

Deep Learning for Face Anti-Spoofing: A Survey [article]

Zitong Yu, Yunxiao Qin, Xiaobai Li, Chenxu Zhao, Zhen Lei, Guoying Zhao
2022 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (36.9 MB)
https://web.archive.org/web/20220526225435/https://arxiv.org/pdf/2106.14948v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL. The file type is application/pdf.

Other Versions

2021 pre-print
arXiv:2106.14948v1 fatcat:o2rkploxuzfs3lbievb5t6ycqm
It covers several novel and insightful components: 1) besides supervision with binary label (e.g., '0' for bonafide vs. '1' for PAs), we also investigate recent methods with pixel-wise supervision (e.g  ...  ., pseudo depth map); 2) in addition to traditional intra-dataset evaluation, we collect and analyze the latest methods specially designed for domain generalization and open-set FAS; and 3) besides commercial  ...  With sufficient pixel-wise supervision, the backbone DenseNet121 converges well and is able to provide patch-wise live/spoof predictions.  ... 
arXiv:2106.14948v2 fatcat:wsheo7hbwvewhjoe6ykwjuqfii
Multiple Versions
Citation

Zitong Yu, Yunxiao Qin, Xiaobai Li, Chenxu Zhao, Zhen Lei, Guoying Zhao. "Deep Learning for Face Anti-Spoofing: A Survey." arXiv (2022)

Towards Learning Structure via Consensus for Face Segmentation and Parsing [article]

Iacopo Masi, Joe Mathai, Wael AbdAlmageed
2020 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (7.6 MB)
https://web.archive.org/web/20200823091213/https://arxiv.org/pdf/1911.00957v3.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Other Versions

2019 pre-print
arXiv:1911.00957v2 fatcat:oww4wwes7fdmfgofxkgcrhppn4
2019 pre-print
arXiv:1911.00957v1 fatcat:r5erupcewfehrbkvts67yzxnwq
Different than current practice, our method enjoys pixel-wise predictions, yet paves the way for fewer artifacts, less sparse masks, and spatially coherent outputs.  ...  robust face segmentation and parsing.  ...  [58] , we take an alternative path towards robust face segmentation and parsing.  ... 
arXiv:1911.00957v3 fatcat:o4pru7yjtfcwdkdjnylepjlqia
Multiple Versions
Citation

Iacopo Masi, Joe Mathai, Wael AbdAlmageed. "Towards Learning Structure via Consensus for Face Segmentation and Parsing." arXiv (2020)

Enabling Verification of Deep Neural Networks in Perception Tasks Using Fuzzy Logic and Concept Embeddings [article]

Gesina Schwalbe, Christian Wirth, Ute Schmid
2022 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (55.0 MB)
https://web.archive.org/web/20220316014914/https://arxiv.org/pdf/2201.00572v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL. The file type is application/pdf.

Other Versions

2022 pre-print
arXiv:2201.00572v1 fatcat:r7degr7xmfhvjnbzhxhcesiije
Applicability is demonstrated on state-of-the-art object detectors for three verification use-cases, where monitoring of rule breaches can reveal detection errors.  ...  ., continuous truth values, and of proper output calibration, which both theoretically and practically show slight benefits.  ...  Acknowledgments The research leading to these results is partly funded by the German Federal Ministry for Economic Affairs and Energy within the project "KI Absicherung -Safe AI for Automated Driving".  ... 
arXiv:2201.00572v2 fatcat:yb6zzribznfhfezf3knftzfifq
Open Access Multiple Versions
Citation

Gesina Schwalbe, Christian Wirth, Ute Schmid. "Enabling Verification of Deep Neural Networks in Perception Tasks Using Fuzzy Logic and Concept Embeddings." arXiv (2022)

A Multi-scale CNN for Affordance Segmentation in RGB Images [chapter]

Anirban Roy, Sinisa Todorovic
2016 Lecture Notes in Computer Science  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (10.2 MB)
https://web.archive.org/web/20190223155747/http://pdfs.semanticscholar.org/496d/1d38a23ebf89037f1e5794f5a34047573d85.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL. The file type is application/pdf.

We are not aware of prior work which starts from pixels, infers mid-level cues, and combines them in a feed-forward fashion for predicting dense affordance maps of a single RGB image.  ...  Our approach uses a deep architecture, consisting of a number of multiscale convolutional neural networks, for extracting mid-level visual cues and combining them toward affordance segmentation.  ...  RGB and RGBD videos provide additional temporal cues for interpreting human-object interactions, and thus allow for robust affordance prediction [4, 7, 42, 43] .  ... 
doi:10.1007/978-3-319-46493-0_12 fatcat:3py62rcasvgkjbknitxntws7vi
Citation

Anirban Roy, Sinisa Todorovic. "A Multi-scale CNN for Affordance Segmentation in RGB Images." Lecture Notes in Computer Science (2016) 186-201

LaneAF: Robust Multi-Lane Detection with Affinity Fields [article]

Hala Abualsaud, Sean Liu, David Lu, Kenny Situ, Akshay Rangesh, Mohan M. Trivedi
2021 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.8 MB)
https://web.archive.org/web/20210825214233/https://arxiv.org/pdf/2103.12040v4.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

Other Versions

2021 pre-print
arXiv:2103.12040v1 fatcat:puelu7chyvf73ikzjirrh5ul7q
2021 pre-print
arXiv:2103.12040v2 fatcat:flhcy5iemvgkrcwhycouqhmsrm
2021 pre-print
arXiv:2103.12040v3 fatcat:7jrrrvqpsvajbhgtlcjxnwohde
This study presents an approach to lane detection involving the prediction of binary segmentation masks and per-pixel affinity fields.  ...  Qualitative and quantitative results obtained on popular lane detection datasets demonstrate the model's ability to detect and cluster lanes effectively and robustly.  ...  We also thank our sponsors and colleagues at LISA, UC San Diego for their support.  ... 
arXiv:2103.12040v4 fatcat:3wxklcwiyncapkr572m2ejoqx4
Multiple Versions
Citation

Hala Abualsaud, Sean Liu, David Lu, Kenny Situ, Akshay Rangesh, Mohan M. Trivedi. "LaneAF: Robust Multi-Lane Detection with Affinity Fields." arXiv (2021)

ConnNet: A Long-Range Relation-Aware Pixel-Connectivity Network for Salient Segmentation

Michael Kampffmeyer, Nanqing Dong, Xiaodan Liang, Yujia Zhang, Eric P. Xing
2019 IEEE Transactions on Image Processing  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (8.3 MB)
https://web.archive.org/web/20200928112257/https://arxiv.org/pdf/1804.07836v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:

2018 pre-print arXiv:1804.07836v1 fatcat:3wo47xh6ubeyhndxp6wd5nwuey

Other Versions

2019 accepted
arXiv:1804.07836v2 fatcat:cz5tlve4xjabxgbf63n3iis3j4
ConnNet predicts connectivity probabilities of each pixel with its neighboring pixels by leveraging multi-level cascade contexts embedded in the image and long-range pixel relations.  ...  Following the intuition that salient objects can be naturally grouped via semantic-aware connectivity between neighboring pixels, we propose a pure Connectivity Net (ConnNet).  ...  For example, given the predicted connectivity cube P and assuming a threshold of 0.5, we predict C5 of a given pixel and C4 of its right-hand neighbor as connected if and only if σ(P i,j,5 ) > 0.5 and  ... 
doi:10.1109/tip.2018.2886997 fatcat:6cikssi6zjauhiqvg7vp2uqgkq
Multiple Versions
Citation

Michael Kampffmeyer, Nanqing Dong, Xiaodan Liang, Yujia Zhang, Eric P. Xing. "ConnNet: A Long-Range Relation-Aware Pixel-Connectivity Network for Salient Segmentation." IEEE Transactions on Image Processing 28.5 (2019) 2518-2529

On Virtual Characters that Can See

Eugene Borovikov, Sergey Yershov
2016 Procedia Computer Science  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (331.3 kB)
https://web.archive.org/web/20190415132907/https://core.ac.uk/download/pdf/82174127.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL. The file type is application/pdf.

Such a VC can be equipped with algorithms to localize humans, recognize and communicate with them.  ...  This CA needs to be fairly seamless, reliable and adaptive. Here we explore a vision-based human-centric approach to the VC design.  ...  , real-world objects detection and classification, most expressive body parts (face+landmarks, hand+fingers) detection and tracking, gesture recognition and interpretation, and discuss their impact on  ... 
doi:10.1016/j.procs.2016.07.475 fatcat:p2za43jnujd2rfnufezcbpijmq
Open Access
Citation

Eugene Borovikov, Sergey Yershov. "On Virtual Characters that Can See." Procedia Computer Science (2016) 528-533

Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks [article]

Jose Oramas, Kaili Wang, Tinne Tuytelaars
2019 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (10.3 MB)
https://web.archive.org/web/20200928191752/https://arxiv.org/pdf/1712.06302v3.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Other Versions

2018 pre-print
arXiv:1712.06302v2 fatcat:bc6twfejazavber62bypzgadjy
2017 pre-print
arXiv:1712.06302v1 fatcat:sbzrpfp25ncyvg2qpra4bmidmm
Interpretation and explanation of deep models is critical towards wide adoption of systems that rely on them.  ...  Then, at test time, we explain the network prediction by accompanying the predicted class label with supporting visualizations derived from the identified features.  ...  ACKNOWLEDGMENTS This work was supported by the FWO SBO project Omnidrone, the VLAIO R&D-project SPOTT , the KU Leuven PDM Grant PDM/16/131, and a NVIDIA GPU grant.  ... 
arXiv:1712.06302v3 fatcat:y7nirvyxszfnzfi37wwnqqyqky
Multiple Versions
Citation

Jose Oramas, Kaili Wang, Tinne Tuytelaars. "Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks." arXiv (2019)

Explainable Artificial Intelligence Methods in Combating Pandemics: A Systematic Review

Felipe Giuste, Wenqi Shi, Yuanda Zhu, Tarun Naren, Monica Isgut, Ying Sha, Li Tong, Mitali Gupte, May D. Wang
2022 IEEE Reviews in Biomedical Engineering  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.1 MB)
https://web.archive.org/web/20220624005432/https://ieeexplore.ieee.org/ielx7/4664312/4664313/09804787.pdf?tp=&arnumber=9804787&isnumber=4664313&ref=

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL. The file type is application/pdf.

This comprehensive review, hopefully, can promote AI adoption in biomedicine and healthcare.  ...  In this systematic review, we introduce common XAI techniques and their utility with specific examples of their application.  ...  Kristan Majors, for her support and guidance on search optimization for the PRISMA chart. We would like to thank Dr.  ... 
doi:10.1109/rbme.2022.3185953 pmid:35737637 fatcat:l7bvseqxrnhvrjy2gbvarnh53e
Open Access
Citation

Felipe Giuste, Wenqi Shi, Yuanda Zhu, Tarun Naren, Monica Isgut, Ying Sha, Li Tong, Mitali Gupte, May D. Wang. "Explainable Artificial Intelligence Methods in Combating Pandemics: A Systematic Review." IEEE Reviews in Biomedical Engineering (2022) 1-17

« Previous Showing results 1 — 15 out of 9,525 results