Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Wada, Yuiga"'
In this work, we address the challenge of developing automatic evaluation metrics for image captioning, with a particular focus on robustness against hallucinations. Existing metrics are often inadequate for handling hallucinations, primarily due to
Externí odkaz:
http://arxiv.org/abs/2409.19255
Establishing an automatic evaluation metric that closely aligns with human judgments is essential for effectively developing image captioning models. Recent data-driven metrics have demonstrated a stronger correlation with human judgments than classi
Externí odkaz:
http://arxiv.org/abs/2402.18091
Autor:
Kaneda, Kanta, Korekata, Ryosuke, Wada, Yuiga, Nagashima, Shunya, Kambara, Motonari, Iioka, Yui, Matsuo, Haruka, Imai, Yuto, Nishimura, Takayuki, Sugiura, Komei
This paper focuses on the DialFRED task, which is the task of embodied instruction following in a setting where an agent can actively ask questions about the task. To address this task, we propose DialMAT. DialMAT introduces Moment-based Adversarial
Externí odkaz:
http://arxiv.org/abs/2311.06855
JaSPICE: Automatic Evaluation Metric Using Predicate-Argument Structures for Image Captioning Models
Image captioning studies heavily rely on automatic evaluation metrics such as BLEU and METEOR. However, such n-gram-based metrics have been shown to correlate poorly with human evaluation, leading to the proposal of alternative metrics such as SPICE
Externí odkaz:
http://arxiv.org/abs/2311.04192
In this study, we aim to develop a model that comprehends a natural language instruction (e.g., "Go to the living room and get the nearest pillow to the radio art on the wall") and generates a segmentation mask for the target everyday object. The tas
Externí odkaz:
http://arxiv.org/abs/2307.08597
Autor:
Tsukamoto, Hideaki, Mita, Yuma, Hanai, Hiroaki, Wada, Yuiga, Nakagawa, Masao, Hirogaki, Toshiki, Aoyama, Eiichi
Publikováno v:
Proceedings of SPIE; October 2024, Vol. 13290 Issue: 1 p132900D-132900D-7, 1196108p
