Rui Zeng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Rui Zeng has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Songwei Pei
School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China
2 shared publications - Yuanzhou Huang
Beijing University of Posts and Telecommunications
2 shared publications - Bingfeng Liu
School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China
1 shared publication - Qian Li
Beijing University of Posts and Telecommunications, Beijing, China
1 shared publication - Shangguang Wang
Beijing University of Posts and Telecommunications
1 shared publication - Shuhuai Wang
School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 12 May 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
DQFormer: Transformer with Decoupled Query Augmentations for End-to-End Multi-Object Tracking
Recent online Transformer-based multi-object tracking methods achieve end-to-end optimization by jointly performing detection and association. However, these trackers apply query augmentations uniformly to detect queries and track queries during training, which may limit their ability to fully exploit distinct features. The different augmentations serve distinct purposes and may have conflicting effects on detection and association. Moreover, the detect queries and the track queries with augmentations contain different semantic information. Jointly feeding these queries into self-attention modules for feature interaction may lead to suppression between the two types of queries. In this paper, we present a novel Transformer-based end-to-end model, DQFormer, which mitigates conflicts and effectively learns task-specific features through the proposed Decoupled Query Augmentation (DQA) strategy. DQA categorizes query augmentations into separate detection and association branches, generating more discriminative queries tailored specifically for detection and association. To align with DQA, we decompose the self-attention module into a Dual Cross-Attention module. Furthermore, a Targeted Label Assignment strategy is applied to the augmented queries in each cross-attention module, helping the model to learn distinct features for tracking. DQFormer achieves competitive detection and association results across the MOT17, MOT20, and DanceTrack datasets.
- 12 May 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
Open AccessDQFormer: Transformer with Decoupled Query Augmentations for End-to-End Multi-Object Tracking
Recent online Transformer-based multi-object tracking methods achieve end-to-end optimization by jointly performing detection and association. However, these trackers apply query augmentations uniformly to detect queries and track queries during training, which may limit their ability to fully exploit distinct features. The different augmentations serve distinct purposes and may have conflicting effects on detection and association. Moreover, the detect queries and the track queries with augmentations contain different semantic information. Jointly feeding these queries into self-attention modules for feature interaction may lead to suppression between the two types of queries. In this paper, we present a novel Transformer-based end-to-end model, DQFormer, which mitigates conflicts and effectively learns task-specific features through the proposed Decoupled Query Augmentation (DQA) strategy. DQA categorizes query augmentations into separate detection and association branches, generating more discriminative queries tailored specifically for detection and association. To align with DQA, we decompose the self-attention module into a Dual Cross-Attention module. Furthermore, a Targeted Label Assignment strategy is applied to the augmented queries in each cross-attention module, helping the model to learn distinct features for tracking. DQFormer achieves competitive detection and association results across the MOT17, MOT20, and DanceTrack datasets.