Search Results for author: Katsuyuki Nakamura

Found 5 papers, 3 papers with code

Class-Difficulty Based Methods for Long-Tailed Visual Recognition

1 code implementation29 Jul 2022 Saptarshi Sinha, Hiroki Ohashi, Katsuyuki Nakamura

Further, we use the difficulty measures of each class to design a novel weighted loss technique called `class-wise difficulty based weighted (CDB-W) loss' and a novel data sampling technique called `class-wise difficulty based sampling (CDB-S)'.

Action Classification Image Classification +4

Sensor-Augmented Egocentric-Video Captioning with Dynamic Modal Attention

1 code implementation7 Sep 2021 Katsuyuki Nakamura, Hiroki Ohashi, Mitsuhiro Okada

We compared the proposed sensor-fusion method with strong baselines on the MMAC Captions dataset and found that using sensor data as supplementary information to the egocentric-video data was beneficial, and that our proposed method outperformed the strong baselines, demonstrating the effectiveness of the proposed method.

Sensor Fusion Video Captioning

Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance

1 code implementation5 Oct 2020 Saptarshi Sinha, Hiroki Ohashi, Katsuyuki Nakamura

We claim that the 'difficulty' of a class as perceived by the model is more important to determine the weighting.

Long-tail Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.