38 citations · 70 across the 4 of their papers we have counts for
4 papers · 1 filter
Class-Difficulty Based Methods for Long-Tailed Visual Recognition
Saptarshi Sinha, Hiroki Ohashi, Katsuyuki Nakamura
Long-tailed datasets are very frequently encountered in real-world use cases where few classes or categories (known as majority or head classes) have higher number of data samples…
Sensor-Augmented Egocentric-Video Captioning with Dynamic Modal Attention
Katsuyuki Nakamura, Hiroki Ohashi, Mitsuhiro Okada
Automatically describing video, or video captioning, has been widely studied in the multimedia field. This paper proposes a new task of sensor-augmented egocentric-video captioning…
Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance
Saptarshi Sinha, Hiroki Ohashi, Katsuyuki Nakamura
Class-imbalance is one of the major challenges in real world datasets, where a few classes (called majority classes) constitute much more data samples than the rest (called minorit…
Attributes' Importance for Zero-Shot Pose-Classification Based on Wearable Sensors
Hiroki Ohashi, Mohammad Al-Naser, Sheraz Ahmed +3
This paper presents a simple yet effective method for improving the performance of zero-shot learning (ZSL). ZSL classifies instances of unseen classes, from which no training data…