Zonghao Guo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zonghao Guo has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Qixiang Ye
University of Chinese Academy of Sciences
5 shared publications - Fang Wan
University of Chinese Academy of Sciences
3 shared publications - Jianbin Jiao
University of Chinese Academy of Sciences, Beijing, China
2 shared publications - Yidan Zhang
University of the Chinese Academy of Sciences, Beijing, China
2 shared publications - Yongqiang Mao
Department of Electronic Engineering, Tsinghua University, Beijing, China
2 shared publications - Yuan Yao
Tsinghua University
2 shared publications
Latest Publications
- 4 October 2026
- Published by Springer Nature
- p. 209-227
NaVLM-PVC: Progressive Visual Compression for Efficient Native-Resolution Encoding in MLLMs
- 4 October 2026
- Published by Springer Nature
- p. 209-227
NaVLM-PVC: Progressive Visual Compression for Efficient Native-Resolution Encoding in MLLMs
- 12 August 2025
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (11) , 7855-7872
Discriminatively Matched Part Tokens for Pointly Supervised Instance Segmentation
- 12 August 2025
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (11) , 7855-7872
Discriminatively Matched Part Tokens for Pointly Supervised Instance Segmentation
- 10 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (8) , 15528-15541
Hierarchical AttentionShift for Pointly Supervised Instance Segmentation
Pointly supervised instance segmentation (PSIS) remains a challenging task when appearance variances across object parts cause semantic inconsistency. In this article, we propose a hierarchical AttentionShift approach, to solve the semantic inconsistency issue through exploiting the hierarchical nature of semantics and the flexibility of key-point representation. The estimation of hierarchical attention is defined upon key-point sets. The representative key points are iteratively estimated spatially and in the feature space to capture the fine-grained semantics and cover the full object extent. Hierarchical AttentionShift is performed at instance, part, and fine-grained levels, optimizing object semantics while promoting the conventional self-attention activation to hierarchical activation with local refinement. Experiments on PASCAL VOC 2012 Aug and MS-COCO 2017 benchmarks show that hierarchical AttentionShift improves the state-of-the-art (SOTA) method by 10.4% and 7.0% upon mean average precision (mAP)50, respectively. When applying hierarchical AttentionShift to the segment anything model (SAM), 9.4% AP improvement on the COCO test-dev is achieved. Hierarchical AttentionShift provides a fresh insight to regularize the self-attention mechanism for fine-grained vision tasks. The code is available at github.com/MingXiangL/AttentionShift.
- 10 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (8) , 15528-15541
Hierarchical AttentionShift for Pointly Supervised Instance Segmentation
Pointly supervised instance segmentation (PSIS) remains a challenging task when appearance variances across object parts cause semantic inconsistency. In this article, we propose a hierarchical AttentionShift approach, to solve the semantic inconsistency issue through exploiting the hierarchical nature of semantics and the flexibility of key-point representation. The estimation of hierarchical attention is defined upon key-point sets. The representative key points are iteratively estimated spatially and in the feature space to capture the fine-grained semantics and cover the full object extent. Hierarchical AttentionShift is performed at instance, part, and fine-grained levels, optimizing object semantics while promoting the conventional self-attention activation to hierarchical activation with local refinement. Experiments on PASCAL VOC 2012 Aug and MS-COCO 2017 benchmarks show that hierarchical AttentionShift improves the state-of-the-art (SOTA) method by 10.4% and 7.0% upon mean average precision (mAP)50, respectively. When applying hierarchical AttentionShift to the segment anything model (SAM), 9.4% AP improvement on the COCO test-dev is achieved. Hierarchical AttentionShift provides a fresh insight to regularize the self-attention mechanism for fine-grained vision tasks. The code is available at github.com/MingXiangL/AttentionShift.
- Top Cited Papers
- 10 November 2024
- Published by Springer Nature
- p. 390-406
LLaVA-UHD: An LMM Perceiving Any Aspect Ratio and High-Resolution Images
- 10 November 2024
- Published by Springer Nature
- p. 390-406
Top Cited PapersLLaVA-UHD: An LMM Perceiving Any Aspect Ratio and High-Resolution Images
- Top Cited Papers
- 7 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (8) , 9454-9468
Conformer: Local Features Coupling Global Representations for Recognition and Detection
With convolution operations, Convolutional Neural Networks (CNNs) are good at extracting local features but experience difficulty to capture global representations. With cascaded self-attention modules, vision transformers can capture long-distance feature dependencies but unfortunately deteriorate local feature details. In this paper, we propose a hybrid network structure, termed Conformer, to take both advantages of convolution operations and self-attention mechanisms for enhanced representation learning. Conformer roots in feature coupling of CNN local features and transformer global representations under different resolutions in an interactive fashion. Conformer adopts a dual structure so that local details and global dependencies are retained to the maximum extent. We also propose a Conformer-based detector (ConformerDet), which learns to predict and refine object proposals, by performing region-level feature coupling in an augmented cross-attention fashion. Experiments on ImageNet and MS COCO datasets validate Conformer's superiority for visual recognition and object detection, demonstrating its potential to be a general backbone network.
- 7 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (8) , 9454-9468
Top Cited PapersConformer: Local Features Coupling Global Representations for Recognition and Detection
With convolution operations, Convolutional Neural Networks (CNNs) are good at extracting local features but experience difficulty to capture global representations. With cascaded self-attention modules, vision transformers can capture long-distance feature dependencies but unfortunately deteriorate local feature details. In this paper, we propose a hybrid network structure, termed Conformer, to take both advantages of convolution operations and self-attention mechanisms for enhanced representation learning. Conformer roots in feature coupling of CNN local features and transformer global representations under different resolutions in an interactive fashion. Conformer adopts a dual structure so that local details and global dependencies are retained to the maximum extent. We also propose a Conformer-based detector (ConformerDet), which learns to predict and refine object proposals, by performing region-level feature coupling in an augmented cross-attention fashion. Experiments on ImageNet and MS COCO datasets validate Conformer's superiority for visual recognition and object detection, demonstrating its potential to be a general backbone network.
- Open Access
Semantic Segmentation for Point Cloud Scenes via Dilated Graph Feature Aggregation and Pyramid Decoders
Semantic segmentation of point clouds generates comprehensive understanding of scenes through densely predicting the category for each point. Due to the unicity of receptive field, semantic segmentation of point clouds remains challenging for the expression of multi-receptive field features, which brings about the misclassification of instances with similar spatial structures. In this paper, we propose a graph convolutional network DGFA-Net rooted in dilated graph feature aggregation (DGFA), guided by multi-basis aggregation loss (MALoss) calculated through Pyramid Decoders. To configure multi-receptive field features, DGFA which takes the proposed dilated graph convolution (DGConv) as its basic building block, is designed to aggregate multi-scale feature representation by capturing dilated graphs with various receptive regions. By simultaneously considering penalizing the receptive field information with point sets of different resolutions as calculation bases, we introduce Pyramid Decoders driven by MALoss for the diversity of receptive field bases. Combining these two aspects, DGFA-Net significantly improves the segmentation performance of instances with similar spatial structures. Experiments on S3DIS, ShapeNetPart and Toronto-3D show that DGFA-Net outperforms the baseline approach, achieving a new state-of-the-art segmentation performance.
Open AccessSemantic Segmentation for Point Cloud Scenes via Dilated Graph Feature Aggregation and Pyramid Decoders
Semantic segmentation of point clouds generates comprehensive understanding of scenes through densely predicting the category for each point. Due to the unicity of receptive field, semantic segmentation of point clouds remains challenging for the expression of multi-receptive field features, which brings about the misclassification of instances with similar spatial structures. In this paper, we propose a graph convolutional network DGFA-Net rooted in dilated graph feature aggregation (DGFA), guided by multi-basis aggregation loss (MALoss) calculated through Pyramid Decoders. To configure multi-receptive field features, DGFA which takes the proposed dilated graph convolution (DGConv) as its basic building block, is designed to aggregate multi-scale feature representation by capturing dilated graphs with various receptive regions. By simultaneously considering penalizing the receptive field information with point sets of different resolutions as calculation bases, we introduce Pyramid Decoders driven by MALoss for the diversity of receptive field bases. Combining these two aspects, DGFA-Net significantly improves the segmentation performance of instances with similar spatial structures. Experiments on S3DIS, ShapeNetPart and Toronto-3D show that DGFA-Net outperforms the baseline approach, achieving a new state-of-the-art segmentation performance.
- Open Access
Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes
Few-shot segmentation of point cloud remains a challenging task, as there is no effective way to convert local point cloud information to global representation, which hinders the generalization ability of point features. In this study, we propose a bidirectional feature globalization (BFG) approach, which leverages the similarity measurement between point features and prototype vectors to embed global perception to local point features in a bidirectional fashion. With point-to-prototype globalization (Po2PrG), BFG aggregates local point features to prototypes according to similarity weights from dense point features to sparse prototypes. With prototype-to-point globalization (Pr2PoG), the global perception is embedded to local point features based on similarity weights from sparse prototypes to dense point features. The sparse prototypes of each class embedded with global perception are summarized to a single prototype for few-shot 3D segmentation based on the metric learning framework. Extensive experiments on S3DIS and ScanNet demonstrate that BFG significantly outperforms the state-of-the-art methods.
Open AccessBidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes
Few-shot segmentation of point cloud remains a challenging task, as there is no effective way to convert local point cloud information to global representation, which hinders the generalization ability of point features. In this study, we propose a bidirectional feature globalization (BFG) approach, which leverages the similarity measurement between point features and prototype vectors to embed global perception to local point features in a bidirectional fashion. With point-to-prototype globalization (Po2PrG), BFG aggregates local point features to prototypes according to similarity weights from dense point features to sparse prototypes. With prototype-to-point globalization (Pr2PoG), the global perception is embedded to local point features based on similarity weights from sparse prototypes to dense point features. The sparse prototypes of each class embedded with global perception are summarized to a single prototype for few-shot 3D segmentation based on the metric learning framework. Extensive experiments on S3DIS and ScanNet demonstrate that BFG significantly outperforms the state-of-the-art methods.
- 4 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (8) , 5252-5265
Convex-Hull Feature Adaptation for Oriented and Densely Packed Object Detection
Detecting oriented and densely packed objects is a challenging problem considering that the receptive field intersection between objects causes spatial feature aliasing. In this paper, we propose a convex-hull feature adaptation (CFA) approach, with the aim to configure convolutional features in accordance with irregular object layouts. CFA roots in the convex-hull feature representation, which defines a set of dynamically sampled feature points guided by the convex intersection over union (CIoU) to bound object extent. CFA pursues optimal feature assignment by constructing convex-hull sets and iteratively splitting positive or negative convex-hulls. By simultaneously considering overlapping convex-hulls and objects and penalizing convex-hulls shared by multiple objects, CFA defines a systematic way to adapt convolutional features on regular grids to objects of irregular shapes. Experiments on DOTA and SKU110K-R datasets show that CFA achieved new state-of-the-art performance for detecting oriented and densely packed objects. CFA also sets a solid baseline for convex polygon prediction on the MS COCO dataset defined for general object detection. Code is available at https://github.com/SDL-GuoZonghao/BeyondBoundingBox .
- 4 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (8) , 5252-5265
Convex-Hull Feature Adaptation for Oriented and Densely Packed Object Detection
Detecting oriented and densely packed objects is a challenging problem considering that the receptive field intersection between objects causes spatial feature aliasing. In this paper, we propose a convex-hull feature adaptation (CFA) approach, with the aim to configure convolutional features in accordance with irregular object layouts. CFA roots in the convex-hull feature representation, which defines a set of dynamically sampled feature points guided by the convex intersection over union (CIoU) to bound object extent. CFA pursues optimal feature assignment by constructing convex-hull sets and iteratively splitting positive or negative convex-hulls. By simultaneously considering overlapping convex-hulls and objects and penalizing convex-hulls shared by multiple objects, CFA defines a systematic way to adapt convolutional features on regular grids to objects of irregular shapes. Experiments on DOTA and SKU110K-R datasets show that CFA achieved new state-of-the-art performance for detecting oriented and densely packed objects. CFA also sets a solid baseline for convex polygon prediction on the MS COCO dataset defined for general object detection. Code is available at https://github.com/SDL-GuoZonghao/BeyondBoundingBox .