activity
20202023
most citedLook, Listen, and Attend: Co-Attention Network for Self-Supervised Audio-Visual Representation Learning

93 citations · 112 across the 10 of their papers we have counts for

collaborators

10 papers

cs.CV2023★ 1 cited

Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervision

Jilan Xu, Junlin Hou, Yuejie Zhang +4

In this paper, we consider the problem of open-vocabulary semantic segmentation (OVS), which aims to segment objects of arbitrary classes instead of pre-defined, closed-set categor…

cs.CV2023★ 11 cited

Tag2Text: Guiding Vision-Language Model via Image Tagging

Xinyu Huang, Youcai Zhang, Jinyu Ma +6

This paper presents Tag2Text, a vision language pre-training (VLP) framework, which introduces image tagging into vision-language models to guide the learning of visual-linguistic…

eess.IV2022

Boosting COVID-19 Severity Detection with Infection-aware Contrastive Mixup Classification

Junlin Hou, Jilan Xu, Nan Zhang +3

This paper presents our solution for the 2nd COVID-19 Severity Detection Competition. This task aims to distinguish the Mild, Moderate, Severe, and Critical grades in COVID-19 ches…

cs.CV2022★ 2 cited

Cross-Field Transformer for Diabetic Retinopathy Grading on Two-field Fundus Images

Junlin Hou, Jilan Xu, Fan Xiao +6

Automatic diabetic retinopathy (DR) grading based on fundus photography has been widely explored to benefit the routine screening and early treatment. Existing researches generally…

eess.IV2022

CMC v2: Towards More Accurate COVID-19 Detection with Discriminative Video Priors

Junlin Hou, Jilan Xu, Nan Zhang +4

This paper presents our solution for the 2nd COVID-19 Competition, occurring in the framework of the AIMIA Workshop at the European Conference on Computer Vision (ECCV 2022). In ou…

cs.CV2022★ 1 cited

Graph Classification via Discriminative Edge Feature Learning

Yang Yi, Xuequan Lu, Shang Gao +2

Spectral graph convolutional neural networks (GCNNs) have been producing encouraging results in graph classification tasks. However, most spectral GCNNs utilize fixed graphs when a…