Zhi Yang

Zhi Yang

Auto-generated profile, based on publicly available information

Zhi Yang

School of Computer Science and Engineering, South China University of Technology, Guangzhou, China

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 October 2022 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
AMAihua Mao
Aihua Mao
ZYZhi Yang
Zhi Yang
KLKen Lin
Ken Lin
JXJun Xuan
Jun Xuan
YLYong-Jin Liu
Yong-Jin Liu
Transformer architectures have recently been introduced into the field of visual question answering (VQA), due to their powerful capabilities of information extraction and fusion. However, existing Transformer-like models, including models using a single Transformer structure and large-scale pre-training generic visual-linguistic models, do not fully utilize both positional information of words in questions and positional information of objects in images, which are shown in this paper to be crucial in VQA tasks. To address this challenge, we propose a novel positional attention guided Transformer-like architecture, which can adaptively extracts positional information within and across the visual and language modalities, and use this information to guide high-level interactions in inter- and intra-modality information flows. In particular, we design and assemble three positional attention modules into a single Transformer-like model MCAN. We show that the positional information introduced in intra-modality interaction can adaptively modulate inter-modality interaction according to different inputs, which plays an important role for visual reasoning. Experimental results demonstrate that our model outperforms the state-of-the-art models and is particularly good at handling object counting questions. Overall, our model achieves the accuracy of 70.10%, 71.27%, 71.52% on the datasets of COCO-QA, VQA v1.0 test-std and VQA v2.0 test-std, respectively. The source code will be publicly available at https://github.com/waizei/PositionalMCAN.

23 May 2023 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
AMAihua Mao
Aihua Mao
ZYZhi Yang
Zhi Yang
WCWanxin Chen
Wanxin Chen
RYRan Yi
Ran Yi
YLYong-Jin Liu
Yong-Jin Liu
3D dense captioning aims to semantically describe each object detected in a 3D scene, which plays a significant role in 3D scene understanding. Previous works lack a complete definition of 3D spatial relationships and the directly integrate visual and language modalities, thus ignoring the discrepancies between the two modalities. To address these issues, we propose a novel complete 3D relationship extraction modality alignment network, which consists of three steps: 3D object detection, complete 3D relationships extraction, and modality alignment caption. To comprehensively capture the 3D spatial relationship features, we define a complete set of 3D spatial relationships, including the local spatial relationship between objects and the global spatial relationship between each object and the entire scene. To this end, we propose a complete 3D relationships extraction module based on message passing and self-attention to mine multi-scale spatial relationship features and inspect the transformation to obtain features in different views. In addition, we propose the modality alignment caption module to fuse multi-scale relationship features and generate descriptions to bridge the semantic gap from the visual space to the language space with the prior information in the word embedding, and help generate improved descriptions for the 3D scene. Extensive experiments demonstrate that the proposed model outperforms the state-of-the-art methods on the ScanRefer and Nr3D datasets.

14 April 2015 in Desalination
Verified
Journal Article
Closed access
SWSonglin Wang
Songlin Wang
XLXiuqing Lu
Xiuqing Lu
NZNing Zhou
Ning Zhou
WXWen-Cheng Xiong
Wen-Cheng Xiong
QZQi Zhang
Qi Zhang
ZYZhi Yang
Zhi Yang

1 March 2017
Verified
Conference Paper
Closed access
YZYang Zhi
Yang Zhi
GXGou Xiantai
Gou Xiantai
WJWeidong Jin
Weidong Jin
XHXu Haowen
Xu Haowen
ZLZeng Lingyuan
Zeng Lingyuan
Aiming at the reverse problem of UAV communication, a reverse method matching known part of priority is presented. First, excavating the frequent items of UAV communication message, to find out the fixed part of the UAV communication protocol format, Then excavating the relationship between UAV flight data detected by radar station and UAV communication data, to find one of the part of the protocol format change part, Finally, According to the requirements of the communication protocol design, excavating the rest of change part. Experiments demonstrate that the recognition speed and accuracy are improved, so the method has high application value in the field of UAV Communication Protocol.