Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Enkhbayar Erdenee"'
Autor:
Seungju Han, Beomsu Kim, Jin Yong Yoo, Seokjun Seo, Sangbum Kim, Enkhbayar Erdenee, Buru Chang
In this paper, we consider mimicking fictional characters as a promising direction for building engaging conversation models. To this end, we present a new practical task where only a few utterances of each fictional character are available to genera
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::702781dfe2cfbfc32cac8b18bf440ca7
http://arxiv.org/abs/2204.10825
http://arxiv.org/abs/2204.10825
Exemplar-based generative models for open-domain conversation produce responses based on the exemplars provided by the retriever, taking advantage of generative models and retrieval models. However, they often ignore the retrieved exemplars while gen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b76a2297a5d428d7ef35c6e80805c5db
http://arxiv.org/abs/2112.06723
http://arxiv.org/abs/2112.06723
Despite the remarkable performance of large-scale generative models in open-domain conversation, they are known to be less practical for building real-time conversation systems due to high latency. On the other hand, retrieval models could return res
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9188e3a2701de33732648b806c6b55d9
Publikováno v:
Cognitive Systems Research. 45:109-123
In this paper, we address the combination of the active learning (AL) and semi-supervised (SSL) learnings, called ASSL, to leverage the strong points of the both learning paradigms for improving the performance of object detection. Considering the pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4d3319497ad409c3f78eda53f067bc09
https://doi.org/10.1016/j.cogsys.2017.05.006
https://doi.org/10.1016/j.cogsys.2017.05.006
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319488806
ECCV Workshops (2)
ECCV Workshops (2)
This paper presents a robust multi-class multi-object tracking (MCMOT) formulated by a Bayesian filtering framework. Multi-object tracking for unlimited object classes is conducted by combining detection responses and changing point detection (CPD) a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4af87c1e3fed1ab97db447692c746a67
https://doi.org/10.1007/978-3-319-48881-3_6
https://doi.org/10.1007/978-3-319-48881-3_6
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319488806
This paper presents a robust multi-class multi-object tracking (MCMOT) formulated by a Bayesian filtering framework. Multi-object tracking for unlimited object classes is conducted by combining detection responses and changing point detection (CPD) a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b32642307615806e1982a07b7079668f
https://doi.org/10.1007/978-3-319-48881-3
https://doi.org/10.1007/978-3-319-48881-3