activity
20182021
most citedDepth CNNs for RGB-D scene recognition: learning from scratch better than transferring from RGB-CNNs

43 citations · 43 across the 1 of their papers we have counts for

collaborators

5 papers

cs.CV2021

Hierarchical Object-to-Zone Graph for Object Navigation

Sixian Zhang, Xinhang Song, Yubing Bai +3

The goal of object navigation is to reach the expected objects according to visual information in the unseen environments. Previous works usually implement deep models to train an…

cs.CV2020

Dataset Bias in Few-shot Image Recognition

Shuqiang Jiang, Yaohui Zhu, Chenlong Liu +3

The goal of few-shot image recognition (FSIR) is to identify novel categories with a small number of annotated samples by exploiting transferable knowledge from training data (base…

cs.CV2019

Scene Recognition with Prototype-agnostic Scene Layout

Gongwei Chen, Xinhang Song, Haitao Zeng +1

Abstract--- Exploiting the spatial structure in scene images is a key research direction for scene recognition. Due to the large intra-class structural diversity, building and mode…

cs.CV2018

Learning Effective RGB-D Representations for Scene Recognition

Xinhang Song, Shuqiang Jiang, Luis Herranz +1

Deep convolutional networks (CNN) can achieve impressive results on RGB scene recognition thanks to large datasets such as Places. In contrast, RGB-D scene recognition is still und…

cs.CV201843 cited

Depth CNNs for RGB-D scene recognition: learning from scratch better than transferring from RGB-CNNs

Xinhang Song, Luis Herranz, Shuqiang Jiang

Scene recognition with RGB images has been extensively studied and has reached very remarkable recognition levels, thanks to convolutional neural networks (CNN) and large scene dat…