activity
20212026
most citedQPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information

17 citations · 25 across the 6 of their papers we have counts for

collaborators
Showing cs.CVShow all

5 papers · 1 filter

cs.CV2026

DetRefiner: Model-Agnostic Detection Refinement with Feature Fusion Transformer

Soichiro Okazaki, Tatsuya Sasaki, Hiroki Ohashi

Open-vocabulary object detection (OVOD) aims to detect both seen and unseen categories, yet existing methods often struggle to generalize to novel objects due to limited integratio…

cs.CV2025

Visually Similar Pair Alignment for Robust Cross-Domain Object Detection

Onkar Krishna, Hiroki Ohashi

Domain gaps between training data (source) and real-world environments (target) often degrade the performance of object detection models. Most existing methods aim to bridge this g…

cs.CV20232 cited

MILA: Memory-Based Instance-Level Adaptation for Cross-Domain Object Detection

Onkar Krishna, Hiroki Ohashi, Saptarshi Sinha

Cross-domain object detection is challenging, and it involves aligning labeled source and unlabeled target domains. Previous approaches have used adversarial training to align feat…

cs.CV20223 cited

Difficulty-Net: Learning to Predict Difficulty for Long-Tailed Recognition

Saptarshi Sinha, Hiroki Ohashi

Long-tailed datasets, where head classes comprise much more training samples than tail classes, cause recognition models to get biased towards the head classes. Weighted loss is on…

cs.CV202117 cited

QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information

Masato Tamura, Hiroki Ohashi, Tomoaki Yoshinaga

We propose a simple, intuitive yet powerful method for human-object interaction (HOI) detection. HOIs are so diverse in spatial distribution in an image that existing CNN-based met…