关注
Spandan Madan
Spandan Madan
Harvard University, Massachusetts Institute of Technology
在 g.harvard.edu 的电子邮件经过验证 - 首页
标题
引用次数
引用次数
年份
Learning visual importance for graphic designs and data visualizations
Z Bylinskii, NW Kim, P O'Donovan, S Alsheikh, S Madan, H Pfister, ...
Proceedings of the 30th Annual ACM symposium on user interface software and …, 2017
1142017
Understanding infographics through textual and visual tag prediction
Z Bylinskii, S Alsheikh, S Madan, A Recasens, K Zhong, H Pfister, ...
arXiv preprint arXiv:1709.09215, 2017
332017
Synthetically trained icon proposals for parsing and summarizing infographics
S Madan, Z Bylinskii, M Tancik, A Recasens, K Zhong, S Alsheikh, ...
arXiv preprint arXiv:1807.10441, 2018
202018
Exploiting the recognition code for elucidating the mechanism of zinc finger protein-DNA interactions
S Dutta, S Madan, D Sundar
BMC genomics 17 (13), 109-125, 2016
82016
On the capability of neural networks to generalize to unseen category-pose combinations
S Madan, T Henry, J Dozier, H Ho, N Bhandari, T Sasaki, F Durand, ...
Center for Brains, Minds and Machines (CBMM), 2020
72020
When and how do CNNs generalize to out-of-distribution category-viewpoint combinations?
S Madan, T Henry, J Dozier, H Ho, N Bhandari, T Sasaki, F Durand, ...
arXiv preprint arXiv:2007.08032, 2020
62020
An ensemble micro neural network approach for elucidating interactions between zinc finger proteins and their target DNA
S Dutta, S Madan, H Parikh, D Sundar
Bmc Genomics 17 (13), 97-107, 2016
62016
Effects of title wording on memory of trends in line graphs
A Newman, Z Bylinskii, S Haroz, S Madan, F Durand, A Oliva
Journal of Vision 18 (10), 837-837, 2018
42018
When pigs fly: Contextual reasoning in synthetic and natural scenes
P Bomatter, M Zhang, D Karev, S Madan, C Tseng, G Kreiman
Proceedings of the IEEE/CVF International Conference on Computer Vision, 255-264, 2021
32021
Small in-distribution changes in 3D perspective and lighting fool both CNNs and Transformers
S Madan, T Sasaki, TM Li, X Boix, H Pfister
arXiv preprint arXiv:2106.16198, 2021
22021
When and how convolutional neural networks generalize to out-of-distribution category–viewpoint combinations
S Madan, T Henry, J Dozier, H Ho, N Bhandari, T Sasaki, F Durand, ...
Nature Machine Intelligence 4 (2), 146-153, 2022
12022
What makes domain generalization hard?
S Madan, L You, M Zhang, H Pfister, G Kreiman
arXiv preprint arXiv:2206.07802, 2022
2022
Three approaches to facilitate DNN generalization to objects in out-of-distribution orientations and illuminations: late-stopping, tuning batch normalization and invariance loss
A Sakai, T Sunagawa, S Madan, K Suzuki, T Katoh, H Kobashi, H Pfister, ...
arXiv preprint arXiv:2111.00131, 2021
2021
To Which Out-Of-Distribution Object Orientations Are DNNs Capable of Generalizing?
A Cooper, X Boix, D Harari, S Madan, H Pfister, T Sasaki, P Sinha
arXiv preprint arXiv:2109.13445, 2021
2021
Parsing and Summarizing Infographics with Synthetically Trained Icon Detection
S Madan, Z Bylinskii, C Nobre, M Tancik, A Recasens, K Zhong, ...
2021 IEEE 14th Pacific Visualization Symposium (PacificVis), 31-40, 2021
2021
ZoomMaps: Using Zoom to Capture Areas of Interest on Images
Z Bylinskii, A Newman, M Tancik, S Madan, F Durand, A Oliva
Journal of Vision 19 (10), 149-149, 2019
2019
When and how CNNs generalize to out-of-distribution category-viewpoint combinations Download PDF Open Website
S Madan, T Henry, JA Dozier, H Ho, N Bhandari, T Sasaki, F Durand, ...
To Which Out-Of-Distribution Object Orientations Are DNNs Capable of Generalizing? Download PDF
A Cooper, X Boix, D Harari, S Madan, H Pfister, T Sasaki, P Sinha
Supplementary Material for When Pigs Fly: Contextual Reasoning in Synthetic and Natural Scenes
P Bomatter, M Zhang, D Karev, S Madan, C Tseng, G Kreiman
系统目前无法执行此操作,请稍后再试。
文章 1–19