QZQi Zou

Qi Zou

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Qi Zou has a total of 71 co-authors. Here are the top co-authors by number of shared publications:

  • Yaping Huang

    Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, Beijing Jiaotong University, Beijing, China

    13 shared publications
  • Xixia Xu

    Bionic Vision System Laboratory, State Key Laboratory of Transducer Technology, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai, China

    9 shared publications
  • Xue Lin

    Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China

    6 shared publications
  • Junbo Liu

    Infrastructure Inspection Research Institute, China Academy of Railway Sciences Corporation Limited, Beijing 100081, China

    3 shared publications
  • Mei Tian

    Beijing Key Laboratory of Traffic Data Analysis and Mining, School of Beijing Jiaotong University, Beijing, China

    3 shared publications
  • Nan Wang

    Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing 100044, China

    3 shared publications

Latest Publications

  • Injecting Task-Specific Clues: Efficient Adaptation of Vision Foundation Models for Domain Generalized Semantic Segmentation

    by Xiaoyu Chen, Qi Zou, Jing Wang, Jianyong Guo, Xinyi Wu, Song Wang, Zhenyao Wu

    Recent advances in Vision Foundation Models (VFMs) have opened new possibilities for Domain-Generalized Semantic Segmentation (DGSS), yet existing parameter-efficient fine-tuning methods fail to fully leverage the inherent generalization capabilities of VFMs under domain shifts. To address this challenge, we propose a novel framework by explicitly leveraging task-specific prior knowledge within VFMs to improve their generalization performance. Specifically, we employ an external lightweight hierarchical Task Clue Injector (TCI) as a side network, where each layer comprises a Semantic-Aware Style Perturbation (SASP) module and a Low-Rank Linear Transformation (LRLT). The SASP performs style perturbation on semantic clusters by leveraging the inherent properties of VFMs to generate task-specific clues in a parameter-free manner. Subsequently, the LRLT is employed to project these task-specific clues into style-agnostic feature representations with minimal parameter updates. Complementing this, we specifically propose an efficient Spatially Adaptive Pixel Decoder (SAPDer) to enable cross-branch feature fusion, which significantly enhances pixel-level spatial awareness. Extensive experiments demonstrate state-of-the-art performance across DGSS benchmarks, while offering a significant advantage in trainable backbone parameters.

  • Hierarchical Contrastive Consistency for Human Pose Estimation in Images and Videos

    by Xixia Xu, Qi Zou, Jiamao Li

    Human pose estimation (HPE) is an invaluable task in computer vision with various practical applications. This paper proposes a novel Hierarchical Contrastive Consistensy constraint (HICCON) to improve the HPE in both images and videos, which describes the input into multi-granular representations at spatial and temporal domain and performs multi-level feature consistency by exploring the characteristic of human structure and time sequence. The hierarchical contrast is conducted at four levels: keypoint-level, part-level, instance-level and clip-level. In spatial, we consider keypoint-level and part-level consistency across instances within frame to enhance the fine-grained keypoint robustness. The former conducts the single keypoint feature contrast across instances to improve the category-specific keypoint features. The latter explores the specific pair-wise features for preserving the instructive relation. In temporal, we develop the instance-level and clip-level feature consistency across frames to capture more discriminative temporal representations. The former discriminates instance features across frames within the same video, whereas the clip-level constraint aims to discriminate consistent features from different videos in order to capture more distinctive temporal features. Extensive experiments on kinds of architectures across datasets i.e, PoseTrack2017, PoseTrack2018 and PoseTrack2021 show the HICCON achieves about 1.5% improvement than baseline. Besides, the proposed method unleashes the potential of the contrastive learning in HPE field.


  • Open Access

    Multi-Person Pose Estimation with Feature Enhancement and Decoupling Based on Contrastive Learning

    by Zhiyuan Liu, Qi Zou, Xixia Xu, Yanting Pei

    Most methods of multi-person pose estimation (MPPE) treat the human detection and keypoint localization separately. They need additional supervision like instance bounding boxes, or complex hand-crafted processes like RoI cropping or grouping. In this article, we propose a novel one-stage MPPE method, named COPE, which unifies human detection and keypoint regression into an end-to-end learnable framework. To handle the challenges plague one-stage MPPE, i.e., instance overlapping and misalignment of local and global context, we design contrastive constraints at two levels of semantic granularity and feature sampling strategies. Based on a whole-process differentiable pipeline, COPE establishes a simple yet effective framework for MPPE without additional instance-level supervision and resource-intensive modules like transformer. Benefit from specially designed contrastive constraints and sampling strategies, COPE can better handle occluded scenes and correct keypoint localization errors. Extensive experiments demonstrate COPE’s superiority. It attains 71.3 AP and 18.0 FPS on COCO val2017, effectively balancing accuracy and speed. Particularly in crowded and occluded scenarios, COPE achieves state-of-the-art performance on CrowdPose and OCHuman, surpassing CID by 0.6 AP and 1.7 AP, respectively. Furthermore, COPE strongly improves generalization performance on the Human-Art benchmark, outperforming ED-Pose by 6.7 AP and ClickPose by 3.7 AP.

  • Rethinking the Sparse End-to-End Multiperson Pose Estimation

    by Xixia Xu, Qi Zou, Jiamao Li

    Current methods of multiperson pose estimation (MPPE) typically treat the human detection and association of joints separately. They introduce complex hand-crafted pose-processes like RoI cropping, NMS and grouping or rely on dense representations to preserve the spatial features. In this article, we dive a deeper thought into this task and propose a simpler and effective framework, termed SparsePose, which can directly predict multiperson joint coordinates from the full image without any post-processes and dense representations. In SparsePose, the full-body instances are decoupled by exploring spatial-aware feature learning (SFL) without box and classification supervision. For improving the quality of instance map, the instance contrastive constraint (ICC) and center correction (CC) strategy are proposed to make the instance-wise spatial feature more discriminative. Importantly, we propose a visibility-guided weighting mechanism to enable model be confident to the visible joint predictions and insensitive to the occlusions or partial bodies. In general, SparsePose is conceptually simpler and plays favorably against the existing counterparts on three benchmarks in terms of both accuracy and efficiency.


  • Open Access

    Inter-image Contrastive Consistency for Multi-Person Pose Estimation

    by Xixia Xu, Yingguo Gao, Xingjia Pan, Ke Yan, Xiaoyu Chen, Qi Zou

    Multi-person pose estimation (MPPE) has achieved impressive progress in recent years. However, due to the large variance of appearances among images or occlusions, the model can hardly learn consistent patterns enough, which leads to severe location jitter and missing issues. In this study, we propose a novel framework, termed Inter-image Contrastive consistency (ICON), to strengthen the keypoint consistency among images for MPPE. Concretely, we consider two-fold consistency constraints, which include single keypoint contrastive consistency (SKCC) and pair relation contrastive consistency (PRCC). The SKCC learns to strengthen the consistency of individual keypoints across images in the same category to improve the category-specific robustness. Only with SKCC, the model can effectively reduce location errors caused by large appearance variations, but remains challenging with extreme postures (e.g., occlusions) due to lack of relational guidance. Therefore, PRCC is proposed to strengthen the consistency of pair-wise joint relation between images to preserve the instructive relation. Cooperating with SKCC, PRCC further improves structure aware robustness in handling extreme postures. Extensive experiments on kinds of architectures across three datasets (i.e., MS-COCO, MPII, CrowdPose) show the proposed ICON achieves substantial improvements over baselines. Furthermore, ICON under the semi-supervised setup can obtain comparable results with the fully-supervised methods using only 30% labeled data.


  • Structure-Enriched Topology Learning For Cross-Domain Multi-Person Pose Estimation

    by Xixia Xu, Qi Zou, Xue Lin

    Human pose estimation has been widely studied with much focus on supervised learning. However, in real applications, a pretrained pose estimation model usually needs be adapted to a novel domain without labels or with sparse labels. Existing domain adaptation methods cannot well deal with it since poses have flexible topological structures and need fine-grained local features. Aiming at the characteristics of human pose, we propose a novel domain adaptation method for multi-person pose estimation (MPPE) to alleviate the human-level shift. Firstly, the training samples of human poses are clustered into groups according to the posture similarity. Within the clustered space, we conduct three adaptation modules: Cross-Attentive Feature Alignment (CAFA), Intra-domain Structure Adaptation (ISA) and Adaptive Human-Topology Adaptation (AHTA). The CAFA adopts a bidirectional spatial attention mechanism to explore fine-grained local feature correlation between two humans, and thus to adaptively aggregate consistent features for adaptation. ISA only works in semi-supervised domain adaptation (SSDA) to exploit semantic relationship of corresponding keypoints for reducing the intra-domain bias. Importantly, we creatively propose an AHTA to enrich human topological knowledge for reducing the inter-domain discrepancy. Specifically, the pose structure and the cross-instance topological relations are modeled via graph networks. This flexible topology learning benefits the occluded or extreme pose inference. Extensive experiments are conducted on two popular benchmarks and additional two challenging datasets. Results demonstrate the competency of our method, which works in unsupervised or semi-supervised modes, compared with the existing supervised approaches.


  • Open Access

    Rail fastener defect inspection method for multi railways based on machine vision

    by Junbo Liu, Yaping Huang, Shengchun Wang, Xinxin Zhao, Qi Zou, Xingyuan Zhang

    Purpose: This research aims to improve the performance of rail fastener defect inspection method for multi railways, to effectively ensure the safety of railway operation.Design/methodology/approach: Firstly, a fastener region location method based on online learning strategy was proposed, which can locate fastener regions according to the prior knowledge of track image and template matching method. Online learning strategy is used to update the template library dynamically, so that the method not only can locate fastener regions in the track images of multi railways, but also can automatically collect and annotate fastener samples. Secondly, a fastener defect recognition method based on deep convolutional neural network was proposed. The structure of recognition network was designed according to the smaller size and the relatively single content of the fastener region. The data augmentation method based on the sample random sorting strategy is adopted to reduce the impact of the imbalance of sample size on recognition performance.Findings: Test verification of the proposed method is conducted based on the rail fastener datasets of multi railways. Specifically, fastener location module has achieved an average detection rate of 99.36%, and fastener defect recognition module has achieved an average precision of 96.82%.Originality/value: The proposed method can accurately locate fastener regions and identify fastener defect in the track images of different railways, which has high reliability and strong adaptability to multi railways.


  • A Stronger Baseline for Seismic Facies Classification With Less Data

    by Xiaoyu Chen, Qi Zou, Xixia Xu, Nan Wang

    With the great success of deep learning in computer vision, the application of convolution neural network (CNN) in seismic facies classification is growing rapidly. However, most of the previous works based on pure state-of-the-art CNN architectures still suffer from coarse segmentation results. In this article, we study the challenges of seismic facies classification and propose a stronger baseline. More specifically, we propose a simple yet effective unsupervised approach named spatial pyramid sampling (SPS) to choose representative samples for training to reduce the labeling costs. Next, we propose a multimodal fusion (M2F) module to extract and fuse the edge and frequency information from selected seismic images to build a stable multimodal representation. Finally, we propose a local-to-global (L2G) module, which improves the recognition power by capturing the local relationship between pixels and enhancing the global context representation. Experimental results demonstrate that the proposed method achieves a superior performance with less labeled training data, especially for small categories.