Zobrazeno 1 - 10
of 68
pro vyhledávání: '"Larry Heck"'
Autor:
Benjamin Z. Reichman, Anirudh Sundar, Christopher Richardson, Tamara Zubatiy, Prithwijit Chowdhury, Aaryan Shah, Jack Truxal, Micah Grimes, Dristi Shah, Woo Ju Chee, Saif Punjwani, Atishay Jain, Larry Heck
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c6f6a8b3e0cb33509affc13ef651fb0f
https://doi.org/10.1109/icassp49357.2023.10096074
https://doi.org/10.1109/icassp49357.2023.10096074
Autor:
Anirudh Sundar, Larry Heck
As humans, we experience the world with all our senses or modalities (sound, sight, touch, smell, and taste). We use these modalities, particularly sight and touch, to convey and interpret specific meanings. Multimodal expressions are central to conv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3fab403212b671ae6ef2cde9c48087aa
http://arxiv.org/abs/2205.06907
http://arxiv.org/abs/2205.06907
Autor:
Sam Masling, Larry Heck, Nancy Xu, James A. Landay, Monica S. Lam, Giovanni Campagna, Michael Du
Publikováno v:
NAACL-HLT
Grounding natural language instructions on the web to perform previously unseen tasks enables accessibility and automation. We introduce a task and dataset to train AI agents from open-domain, step-by-step instructions originally written for people.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9fcbc912aa5273941c43595c3e14e322
https://doi.org/10.18653/v1/2021.naacl-main.80
https://doi.org/10.18653/v1/2021.naacl-main.80
Autor:
Dawei Li, C.-C. Jay Kuo, Jie Zhang, Shalini Ghosh, Larry Heck, Serafettin Tasci, Heming Zhang, Junting Zhang
Publikováno v:
WACV
Deep neural networks (DNNs) often suffer from "catastrophic forgetting" during incremental learning (IL) --- an abrupt degradation of performance on the original set of classes when the training objective is adapted to a newly added set of classes. E
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::20d677a2c0a827f3d0459267901b8327
https://doi.org/10.1109/wacv45572.2020.9093365
https://doi.org/10.1109/wacv45572.2020.9093365
Autor:
Sung-Soo Kim, Minkyoo Shin, Dhananjaya Gowda, Jiyeon Kim, Abhinav Garg, Shatrughan Singh, Eunhyang Kim, Mehul Kumar, Kwangyoun Kim, Chanwoo Kim, Changwoo Han, Larry Heck, Kyungmin Lee
Publikováno v:
ASRU
In this paper, we present an end-to-end training framework for building state-of-the-art end-to-end speech recognition systems. Our training system utilizes a cluster of Central Processing Units(CPUs) and Graphics Processing Units (GPUs). The entire
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c7820ff2e2695f699fd04128413983fd
http://arxiv.org/abs/1912.11040
http://arxiv.org/abs/1912.11040
Publikováno v:
IROS
Using models to represent information about the world is a well known paradigm for successful robot control in the real world. Numerous methods exist today that can leverage these models to make robots perform tasks, either by directly exploiting the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::64e108840c413a971a93f354679a30f9
https://doi.org/10.1109/iros40897.2019.8968211
https://doi.org/10.1109/iros40897.2019.8968211
Autor:
Dhruv Batra, Stefan Lee, Hongxia Jin, Ramprasaath R. Selvaraju, Yilin Shen, Devi Parikh, Larry Heck, Shalini Ghosh
Publikováno v:
ICCV
Many vision and language models suffer from poor visual grounding - often falling back on easy-to-learn language priors rather than basing their decisions on visual concepts in the image. In this work, we propose a generic approach called Human Impor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b57485ecee857def729c6ede488fc010
https://doi.org/10.1109/iccv.2019.00268
https://doi.org/10.1109/iccv.2019.00268
Autor:
Shalini Ghosh, C.-C. Jay Kuo, Jie Zhang, Larry Heck, Junting Zhang, Stephen Walsh, Heming Zhang
Publikováno v:
IJCAI
The key challenge of generative Visual Dialogue (VD) systems is to respond to human queries with informative answers in natural and contiguous conversation flow. Traditional Maximum Likelihood Estimation-based methods only learn from positive respons
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::874a0f4d1370885dc00f3edb98680e56
https://doi.org/10.24963/ijcai.2019/144
https://doi.org/10.24963/ijcai.2019/144
Publikováno v:
SEC
Object detection models shipped with camera-equipped edge devices cannot cover the objects of interest for every user. Therefore, the incremental learning capability is a critical feature for a robust and personalized object detection system that man
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::54916458c6ee0f525ca874f99c8fdec9
Autor:
Larry Heck, Stanley Peters, Pongtep Angkititrakul, Fuliang Weng, John H. L. Hansen, Elizabeth Shriberg
Publikováno v:
IEEE Signal Processing Magazine. 33:49-60
Automotive technology rapidly advances with increasing connectivity and automation. These advancements aim to assist safe driving and improve user travel experience. Before the realization of a full automation, in-vehicle dialog systems may reduce th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::74caf0b6537f08beacd11a5d2518fc54
https://doi.org/10.1109/msp.2016.2599201
https://doi.org/10.1109/msp.2016.2599201