no code implementations • 31 Mar 2024 • Yitian Tao, Liyan Ma, Jing Yu, Han Zhang
To ensure the semantic consistency of the retrieved cross modal prior knowledge, a cross-modal semantic alignment module (SAM) is proposed.
no code implementations • 5 Mar 2024 • Yu Chen, Liyan Ma, Liping Jing, Jian Yu
Humans can easily distinguish the known and unknown categories and can recognize the unknown object by learning it once instead of repeating it many times without forgetting the learned object.
no code implementations • 21 Oct 2023 • Weiming Huang, Qinghua Huang, Liyan Ma, Chuan Wang
Sound event localization and detection (SELD) involves sound event detection (SED) and direction of arrival (DoA) estimation tasks.
1 code implementation • 25 Aug 2023 • Yan Sun, Xueling Feng, Liyan Ma, Long Hu, Mark Nixon
To fully exploit the complementary nature of the two modalities, a novel triple branch gait recognition framework, TriGait, is proposed in this paper.
no code implementations • 23 Feb 2023 • Jinan Yu, Liyan Ma, Zhenglin Li, Yan Peng, Shaorong Xie
Open-world object detection (OWOD) is a challenging problem that combines object detection with incremental learning and open-set learning.
no code implementations • 4 Nov 2020 • Li Tian, Liyan Ma, Zhijie Wen, Shaorong Xie, Yupeng Xu
Diabetic retinopathy (DR) is one of the leading causes of blindness.
no code implementations • 31 Mar 2019 • Xiaoye Sun, Liyan Ma, Gongyan Li
To solve the red jujube classification problem, this paper designs a convolutional neural network model with low computational cost and high classification accuracy.