no code implementations • 28 Nov 2023 • Takehiko Ohkawa, Takuma Yagi, Taichi Nishimura, Ryosuke Furuta, Atsushi Hashimoto, Yoshitaka Ushiku, Yoichi Sato
We propose a novel benchmark for cross-view knowledge transfer of dense video captioning, adapting models from web instructional videos with exocentric views to an egocentric view.
1 code implementation • 2 Nov 2023 • Keisuke Shirai, Cristian C. Beltran-Hernandez, Masashi Hamaya, Atsushi Hashimoto, Shohei Tanaka, Kento Kawaharazuka, Kazutoshi Tanaka, Yoshitaka Ushiku, Shinsuke Mori
By generating PDs from language instruction and scene observation, we can drive symbolic planners in a language-guided framework.
1 code implementation • 19 Oct 2023 • Shusaku Sone, Jiaxin Ma, Atsushi Hashimoto, Naoya Chiba, Yoshitaka Ushiku
Matching, a task to optimally assign limited resources under constraints, is a fundamental technology for society.
no code implementations • 6 Jul 2023 • Shiqi Yang, Atsushi Hashimoto, Yoshitaka Ushiku
In recent years large model trained on huge amount of cross-modality data, which is usually be termed as foundation model, achieves conspicuous accomplishment in many fields, such as image recognition and generation.
1 code implementation • 20 Apr 2023 • Qing Yu, Atsushi Hashimoto, Yoshitaka Ushiku
To transfer the knowledge learned from a labeled source domain to an unlabeled target domain, many studies have worked on universal domain adaptation (UniDA), where there is no constraint on the label sets of the source domain and target domain.
no code implementations • 21 Sep 2022 • Taichi Nishimura, Atsushi Hashimoto, Yoshitaka Ushiku, Hirotaka Kameko, Shinsuke Mori
However, unlike DVC, in recipe generation, recipe story awareness is crucial, and a model should extract an appropriate number of events in the correct order and generate accurate sentences based on them.
no code implementations • COLING 2022 • Keisuke Shirai, Atsushi Hashimoto, Taichi Nishimura, Hirotaka Kameko, Shuhei Kurita, Yoshitaka Ushiku, Shinsuke Mori
We present a new multimodal dataset called Visual Recipe Flow, which enables us to learn each cooking action result in a recipe text.
1 code implementation • 4 Feb 2022 • rintaro yanagi, Atsushi Hashimoto, Shusaku Sone, Naoya Chiba, Jiaxin Ma, Yoshitaka Ushiku
Instead of only optimizing the feature extractor for a matching algorithm, we propose a learning-based matching module optimized to the jointly-trained feature extractor.
no code implementations • 29 Sep 2021 • Shusaku Sone, Atsushi Hashimoto, Jiaxin Ma, rintaro yanagi, Naoya Chiba, Yoshitaka Ushiku
Assignment, a task to match a limited number of elements, is a fundamental problem in informatics.
1 code implementation • 6 Jul 2021 • Takehiko Ohkawa, Takuma Yagi, Atsushi Hashimoto, Yoshitaka Ushiku, Yoichi Sato
We validated our method on domain adaptation of hand segmentation from real and simulation images.
no code implementations • NeurIPS 2021 • Shusaku Sone, Jiaxin Ma, Atsushi Hashimoto, Naoya Chiba, Yoshitaka Ushiku
Assignment, a task to match a limited number of elements, is a fundamental problem in informatics.
1 code implementation • EACL 2021 • Ukyo Honda, Yoshitaka Ushiku, Atsushi Hashimoto, Taro Watanabe, Yuji Matsumoto
Unsupervised image captioning is a challenging task that aims at generating captions without the supervision of image-sentence pairs, but only with images and sentences drawn from different sources and object labels detected from the images.
1 code implementation • CVPR 2021 • Qing Yu, Atsushi Hashimoto, Yoshitaka Ushiku
Hence, we consider a new realistic setting called Noisy UniDA, in which classifiers are trained with noisy labeled data from the source domain and unlabeled data with an unknown class distribution from the target domain.
no code implementations • LREC 2020 • Taichi Nishimura, Suzushi Tomori, Hayato Hashimoto, Atsushi Hashimoto, Yoko Yamakata, Jun Harashima, Yoshitaka Ushiku, Shinsuke Mori
Visual grounding is provided as bounding boxes to image sequences of recipes, and each bounding box is linked to an element of the workflow.
1 code implementation • ECCV 2020 • Ryuhei Takahashi, Atsushi Hashimoto, Motoharu Sonogashira, Masaaki Iiyama
In practice, this is an important problem in UDA; as we do not know labels in target domain datasets, we do not know whether or not its distribution is identical to that in the source domain dataset.
no code implementations • WS 2019 • Taichi Nishimura, Atsushi Hashimoto, Shinsuke Mori
Multimedia procedural texts, such as instructions and manuals with pictures, support people to share how-to knowledge.
no code implementations • 23 May 2019 • Ryo Yonetani, Tomohiro Takahashi, Atsushi Hashimoto, Yoshitaka Ushiku
This work addresses a new problem that learns generative adversarial networks (GANs) from multiple data collections that are each i) owned separately by different clients and ii) drawn from a non-identical distribution that comprises different classes.
no code implementations • CVPR 2018 • Yuki Fujimura, Masaaki Iiyama, Atsushi Hashimoto, Michihiko Minoh
Images captured in participating media such as murky water, fog, or smoke are degraded by scattered light.
no code implementations • IJCNLP 2017 • Atsushi Ushiku, Hayato Hashimoto, Atsushi Hashimoto, Shinsuke Mori
In this paper, we focus on procedure execution videos, in which a human makes or repairs something and propose a method for generating procedural texts from them.
no code implementations • 3 Mar 2017 • Takuro Ina, Atsushi Hashimoto, Masaaki Iiyama, Hidekazu Kasahara, Mikihiko Mori, Michihiko Minoh
The highlights of this paper are the following two mathematical observations: first, spectral clustering's intrinsic property of an outlier cluster formation, and second, the singularity of an outlier cluster with a valid cluster number.