Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Shagun Uppal"'
Autor:
Navonil Majumder, Soujanya Poria, Roger Zimmermann, Shagun Uppal, Devamanyu Hazarika, Amir Zadeh, Sarthak Bhagat
Publikováno v:
Information Fusion. 77:149-171
Deep Learning and its applications have cascaded impactful research and development with a diverse range of modalities present in the real-world data. More recently, this has enhanced research interests in the intersection of the Vision and Language
Autor:
Devansh Gupta, Aditya Saini, Sarthak Bhagat, Shagun Uppal, Rishi Raj Jain, Drishti Bhasin, Ponnurangam Kumaraguru, Rajiv Ratn Shah
Publikováno v:
2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).
Autor:
Sahil Goyal, Shagun Uppal, Sarthak Bhagat, Dhroov Goel, Sakshat Mali, Yi Yu, Yifang Yin, Rajiv Ratn Shah
Publikováno v:
Proceedings of the 4th ACM International Conference on Multimedia in Asia.
Autor:
Devansh Gupta, Drishti Bhasin, Sarthak Bhagat, Shagun Uppal, Ponnurangam Kumaraguru, Rajiv Ratn Shah
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:12961-12962
Targeted image retrieval has long been a challenging problem since each person has a different perception of different features leading to inconsistency among users in describing the details of a particular image. Due to this, each user needs a syste
Visual Question Generation (VQG) is the task of generating natural questions based on an image. Popular methods in the past have explored image-to-sequence architectures trained with maximum likelihood which have demonstrated meaningful generated que
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b581c089c633e5d36a12c69bc31896c4
http://arxiv.org/abs/2005.07771
http://arxiv.org/abs/2005.07771
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030454388
ECIR (1)
ECIR (1)
Predicting the runtime complexity of a programming code is an arduous task. In fact, even for humans, it requires a subtle analysis and comprehensive knowledge of algorithms to predict time complexity with high fidelity, given any code. As per Turing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f499c10bb652a77c92cb0b93f3a2e585
https://doi.org/10.1007/978-3-030-45439-5_21
https://doi.org/10.1007/978-3-030-45439-5_21
Publikováno v:
Computer Vision – ECCV 2020 Workshops ISBN: 9783030654139
ECCV Workshops (6)
ECCV Workshops (6)
Disentangling underlying feature attributes within an image with no prior supervision is a challenging task. Models that can disentangle attributes well, provide greater interpretability and control. In this paper, we propose a self-supervised framew
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::855dd8273c36a78a74deda90921db8d6
https://doi.org/10.1007/978-3-030-65414-6_38
https://doi.org/10.1007/978-3-030-65414-6_38
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585914
ECCV (23)
ECCV (23)
We introduce MGP-VAE (Multi-disentangled-features Gaussian Processes Variational AutoEncoder), a variational autoencoder which uses Gaussian processes (GP) to model the latent space for the unsupervised learning of disentangled representations in vid
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2a6591a4cfaa86311cbf43c13b0a50f2
https://doi.org/10.1007/978-3-030-58592-1_7
https://doi.org/10.1007/978-3-030-58592-1_7
Publikováno v:
ICVGIP
Deep generative models like variational autoencoders approximate the intrinsic geometry of high dimensional data manifolds by learning low-dimensional latent-space variables and an embedding function. The geometric properties of these latent spaces h