Minghao Zhu

Minghao Zhu

Auto-generated profile, based on publicly available information

Minghao Zhu

College of Electronics and Information Engineering, Tongji University, Shanghai, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
8 May 2024 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
XLXiao Lin
Xiao Lin
MZMinghao Zhu
Minghao Zhu
RDRonghao Dang
Ronghao Dang
GZGuangliang Zhou
Guangliang Zhou
SSShaolong Shu
Shaolong Shu
QCQijun Chen
Qijun Chen
Most of existing category-level object pose estimation methods devote to learning the object category information from point cloud modality. However, the scale of 3D datasets is limited due to the high cost of 3D data collection and annotation. Consequently, the category features extracted from these limited point cloud samples may not be comprehensive. This motivates us to investigate whether we can draw on knowledge of other modalities to obtain category information. Inspired by this motivation, we propose CLIPose, a novel 6D pose framework that employs the pre-trained vision-language model to develop better learning of object category information, which can fully leverage abundant semantic knowledge in image and text modalities. To make the 3D encoder learn category-specific features more efficiently, we align representations of three modalities in feature space via multi-modal contrastive learning. In addition to exploiting the pre-trained knowledge of the CLIP’s model, we also expect it to be more sensitive with pose parameters. Therefore, we introduce a prompt tuning approach to fine-tune image encoder while we incorporate rotations and translations information in the text descriptions. CLIPose achieves state-of-the-art performance on two mainstream benchmark datasets, REAL275 and CAMERA25, and runs in real-time during inference (40FPS).

26 October 2023
Verified
Conference Paper
Open access
MZMinghao Zhu
Minghao Zhu
XLXiao Lin
Xiao Lin
RDRonghao Dang
Ronghao Dang
CLChengju Liu
Chengju Liu
QCQijun Chen
Qijun Chen
As the most essential property in a video, motion information is critical to a robust and generalized video representation. To inject motion dynamics, recent works have adopted frame difference as the source of motion information in video contrastive learning, considering the trade-off between quality and cost. However, existing works align motion features at the instance level, which suffers from spatial and temporal weak alignment across modalities. In this paper, we present a Fine-grained Motion Alignment (FIMA) framework, capable of introducing well-aligned and significant motion information. Specifically, we first develop a dense contrastive learning framework in the spatiotemporal domain to generate pixel-level motion supervision. Then, we design a motion decoder and a foreground sampling strategy to eliminate the weak alignments in terms of time and space. Moreover, a frame-level motion contrastive loss is presented to improve the temporal diversity of the motion features. Extensive experiments demonstrate that the representations learned by FIMA possess great motion-awareness capabilities and achieve state-of-the-art or competitive results on downstream tasks across UCF101, HMDB51, and Diving48 datasets. Code is available at https://github.com/ZMHH-H/FIMA.

1 January 2026 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
QZQinyang Zeng
Qinyang Zeng
CLChengju Liu
Chengju Liu
XZXun Zhou
Xun Zhou
MZMinghao Zhu
Minghao Zhu
QCQijun Chen
Qijun Chen