Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Anima Majumder"'
Publikováno v:
2022 International Conference on Robotics and Automation (ICRA).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::65095a33d548cbea2f709aa5a994a421
https://doi.org/10.1109/icra46639.2022.9812281
https://doi.org/10.1109/icra46639.2022.9812281
Autor:
Madhu Babu Vankadari, Vishal Bhutani, Omprakash Jha, Anima Majumder, Samrat Dutta, Swagat Kumar
Publikováno v:
IROS
In this paper, we propose an unsupervised deep learning framework with Bayesian inference for improving the accuracy of per-pixel depth prediction from monocular RGB images. The proposed framework predicts confidence map along with depth and pose inf
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3c31e75d5b6a23e6a8fdac0c821b2ac6
https://doi.org/10.1109/iros45743.2020.9341024
https://doi.org/10.1109/iros45743.2020.9341024
Autor:
Swagat Kumar, Chandan Kumar Singh, Vivek Kumar Gangwar, Prakash Chanderlal Ambwani, Anima Majumder, Rajesh Sinha
Publikováno v:
IJCNN
Capsule Network (CapsNet) has motivated researchers to work on it due to its distinct capability of retaining spatial correlations between image features. However, its applicability is still limited because of its intensive computational cost, memory
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e7f31e67d1658cf134b5c89c128f1f3e
https://doi.org/10.1109/ijcnn48605.2020.9206785
https://doi.org/10.1109/ijcnn48605.2020.9206785
Publikováno v:
IEEE Transactions on Cybernetics. 48:103-114
This paper presents a novel automatic facial expressions recognition system (AFERS) using the deep network framework. The proposed AFERS consists of four steps: 1) geometric features extraction; 2) regional local binary pattern (LBP) features extract
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c46fd0c592e4d39fec3efbddb8a50a57
https://doi.org/10.1109/tcyb.2016.2625419
https://doi.org/10.1109/tcyb.2016.2625419
Publikováno v:
Advances on Robotic Item Picking ISBN: 9783030356781
In this chapter, we provide details of the system that was used for our participation in the Amazon Robotics Challenge 2017 held in Nagoya, Japan. Our hardware system comprised of an UR10 robot manipulator with an eye-in-hand 2D/3D vision system and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::329746a34b04864e1fa90b15d5ff2384
https://doi.org/10.1007/978-3-030-35679-8_10
https://doi.org/10.1007/978-3-030-35679-8_10
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030586034
ECCV (28)
ECCV (28)
In this paper, we look into the problem of estimating per-pixel depth maps from unconstrained RGB monocular night-time images which is a difficult task that has not been addressed adequately in the literature. The state-of-the-art day-time depth esti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c54c4ddc35375873d7e212c3ff29ef75
https://doi.org/10.1007/978-3-030-58604-1_27
https://doi.org/10.1007/978-3-030-58604-1_27
Publikováno v:
RO-MAN
In this paper, we propose an end-to-end self-supervised feature representation network for imitation learning. The proposed network incorporates a novel multi-level spatial attention module to amplify the relevant and suppress the irrelevant informat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ad25512c1eb5a563dd0260b778033f48
https://doi.org/10.1109/ro-man46459.2019.8956303
https://doi.org/10.1109/ro-man46459.2019.8956303
Publikováno v:
RO-MAN
The presented work focuses on automatic recognition of object classes while ensuring near real-time training required for recognizing a new object not seen previously. This is achieved by proposing a two-stage hierarchical deep learning framework whi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b6d8132cda7129c03d28d34a6f5b6471
https://doi.org/10.1109/ro-man46459.2019.8956366
https://doi.org/10.1109/ro-man46459.2019.8956366
Publikováno v:
IJCAI
This paper presents a new GAN-based deep learning framework for estimating absolute scale awaredepth and ego motion from monocular images using a completely unsupervised mode of learning.The proposed architecture uses two separate generators to learn
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d4f3cbd8905c2643b0c925609b6ff141
https://doi.org/10.24963/ijcai.2019/787
https://doi.org/10.24963/ijcai.2019/787
Autor:
Swagat Kumar, Chandan Kumar Singh, Karan Narain, Harsh Vardhan Singh, Vivek Kumar Gangwar, Anima Majumder
Publikováno v:
IJCNN
Automatic recognition of text, such as a batch code printed on a box placed on a moving conveyor belt, is still a challenging problem. This paper proposes an end-to-end character recognition technique while addressing the major challenges encountered
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::388566375b6a07cb004ba8717ba7d5e8
https://doi.org/10.1109/ijcnn.2019.8852303
https://doi.org/10.1109/ijcnn.2019.8852303