Zobrazeno 1 - 10
of 1 124
pro vyhledávání: '"Kim, Jong hwan"'
Recent studies have addressed intricate phonological phenomena in French, relying on either extensive linguistic knowledge or a significant amount of sentence-level pronunciation data. However, creating such resources is expensive and non-trivial. To
Externí odkaz:
http://arxiv.org/abs/2410.05698
While many FSCIL studies have been undertaken, achieving satisfactory performance, especially during incremental sessions, has remained challenging. One prominent challenge is that the encoder, trained with an ample base session training set, often u
Externí odkaz:
http://arxiv.org/abs/2309.02833
Autor:
Lee, Sun-Kyung, Kim, Jong-Hwan
This paper proposes a system capable of recognizing a speaker's utterance-level emotion through multimodal cues in a video. The system seamlessly integrates multiple AI models to first extract and pre-process multimodal information from the raw video
Externí odkaz:
http://arxiv.org/abs/2308.14320
Sensor fusion approaches for intelligent self-driving agents remain key to driving scene understanding given visual global contexts acquired from input sensors. Specifically, for the local waypoint prediction task, single-modality networks are still
Externí odkaz:
http://arxiv.org/abs/2308.02126
Phrase break prediction is a crucial task for improving the prosody naturalness of a text-to-speech (TTS) system. However, most proposed phrase break prediction models are monolingual, trained exclusively on a large amount of labeled data. In this pa
Externí odkaz:
http://arxiv.org/abs/2306.02579
Few-shot class-incremental learning (FSCIL) presents the primary challenge of balancing underfitting to a new session's task and forgetting the tasks from previous sessions. To address this challenge, we develop a simple yet powerful learning scheme
Externí odkaz:
http://arxiv.org/abs/2305.16687
Autor:
Choi, Tae-Min, Kim, Jong-Hwan
Publikováno v:
2023 IEEE International Conference on Robotics and Automation (ICRA), 9289-9295
In this paper, we explore incremental few-shot object detection (iFSD), which incrementally learns novel classes using only a few examples without revisiting base classes. Previous iFSD works achieved the desired results by applying meta-learning. Ho
Externí odkaz:
http://arxiv.org/abs/2302.09779