Zobrazeno 1 - 10
of 21
pro vyhledávání: '"RoyChowdhury, Aruni"'
Autor:
Liao, Haofu, RoyChowdhury, Aruni, Li, Weijian, Bansal, Ankan, Zhang, Yuting, Tu, Zhuowen, Satzoda, Ravi Kumar, Manmatha, R., Mahadevan, Vijay
We present a new formulation for structured information extraction (SIE) from visually rich documents. It aims to address the limitations of existing IOB tagging or graph-based formulations, which are either overly reliant on the correct ordering of
Externí odkaz:
http://arxiv.org/abs/2307.07929
Autor:
Sharma, Gopal, Dash, Bidya, RoyChowdhury, Aruni, Gadelha, Matheus, Loizou, Marios, Cao, Liangliang, Wang, Rui, Learned-Miller, Erik, Maji, Subhransu, Kalogerakis, Evangelos
We present PriFit, a semi-supervised approach for label-efficient learning of 3D point cloud segmentation networks. PriFit combines geometric primitive fitting with point-based representation learning. Its key idea is to learn point representations w
Externí odkaz:
http://arxiv.org/abs/2112.13942
While deep face recognition has benefited significantly from large-scale labeled data, current research is focused on leveraging unlabeled data to further boost performance, reducing the cost of human annotation. Prior work has mostly been in control
Externí odkaz:
http://arxiv.org/abs/2007.06995
Autor:
Gadelha, Matheus, RoyChowdhury, Aruni, Sharma, Gopal, Kalogerakis, Evangelos, Cao, Liangliang, Learned-Miller, Erik, Wang, Rui, Maji, Subhransu
Publikováno v:
16th European Conference on Computer Vision (ECCV 2020)
The problems of shape classification and part segmentation from 3D point clouds have garnered increasing attention in the last few years. Both of these problems, however, suffer from relatively small training sets, creating the need for statistically
Externí odkaz:
http://arxiv.org/abs/2003.13834
Autor:
RoyChowdhury, Aruni, Chakrabarty, Prithvijit, Singh, Ashish, Jin, SouYoung, Jiang, Huaizu, Cao, Liangliang, Learned-Miller, Erik
This work addresses the unsupervised adaptation of an existing object detector to a new target domain. We assume that a large number of unlabeled videos from this domain are readily available. We automatically obtain labels on the target data by usin
Externí odkaz:
http://arxiv.org/abs/1904.07305
Autor:
Jin, SouYoung, RoyChowdhury, Aruni, Jiang, Huaizu, Singh, Ashish, Prasad, Aditya, Chakraborty, Deep, Learned-Miller, Erik
Important gains have recently been obtained in object detection by using training objectives that focus on {\em hard negative} examples, i.e., negative examples that are currently rated as positive or ambiguous by the detector. These examples can str
Externí odkaz:
http://arxiv.org/abs/1808.04285
The recent explosive growth in convolutional neural network (CNN) research has produced a variety of new architectures for deep learning. One intriguing new architecture is the bilinear CNN (B-CNN), which has shown dramatic performance gains on certa
Externí odkaz:
http://arxiv.org/abs/1506.01342
We present a simple and effective architecture for fine-grained visual recognition called Bilinear Convolutional Neural Networks (B-CNNs). These networks represent an image as a pooled outer product of features derived from two CNNs and capture local
Externí odkaz:
http://arxiv.org/abs/1504.07889
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
IEEE Transactions on Pattern Analysis & Machine Intelligence. Jun2018, Vol. 40 Issue 6, p1309-1322. 14p.