Yuyu Guo
Yuyu Guo has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Heng Tao Shen
Tongji University, Shanghai, China
2 shared publications - Jingkuan Song
Tongji University, Shanghai, China
2 shared publications - Lianli Gao
University of Electronic Science and Technology of China, Chengdu, China
2 shared publications - Cheng Chen
Ant Group
1 shared publication - Hang Yu
Ant Group
1 shared publication - Lingchen Meng
School of CS, Fudan University
1 shared publication
Latest Publications
- 13 September 2026
- Published by Springer Nature
- p. 188-206
VLZip: Unified Visual and Textual Compression for Interleaved Long-Context Modeling
- 13 September 2026
- Published by Springer Nature
- p. 188-206
VLZip: Unified Visual and Textual Compression for Interleaved Long-Context Modeling
- 14 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 25 (15209210) , 979-992
AMANet: Adaptive Multi-Path Aggregation for Learning Human 2D-3D Correspondences
Learning human 2D-3D correspondences aims to map all human 2D pixels to a 3D human template, namely human densepose estimation, involving surface patch recognition (i.e., Index-to-Patch (I)) and regression of patch-specific UV coordinates. Despite recent progress, it remains challenging especially under the condition of in the wild, where RGB images capture real-world scenes with backgrounds, occlusions, scale variations, and postural diversity. In this paper, we address three vital problems in this task: 1) how to perceive multi-scale visual information for instances ‘`in the wild’'; 2) how to design learning objectives to address the precise instance representation harassed by multiple instances in one bounding box phenomenon; and 3) how to boost the performance of index-to-patch prediction faced by limited supervision. To tackle problems above, we propose an end-to-end deep Adaptive Multi-path Aggregation network (AMA-net) for Human DensePose Estimation. First, we introduce an adaptive multi-path aggregation algorithm to extract varying-sized instance-level feature maps, which capture multi-scale information of a bounding-box and are then utilized for analyzing different instances. Second, we adopt an instance augmentation learning objective to further distinguish the target instance from other interference instances. Third, taking advantage of 2D human parsers that are trained from sufficient annotations, we introduce a task transformer that bridges the ‘`gap’' between 2D human parsing and densepose estimation, thus benefiting the performance of densepose estimator. Experimental results on the challenging Dense-COCO dataset demonstrate that our approach sets a new record, and it significantly outperforms the state-of-the-art methods. Codes and models are publicly available.
- 14 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 25 (15209210) , 979-992
AMANet: Adaptive Multi-Path Aggregation for Learning Human 2D-3D Correspondences
Learning human 2D-3D correspondences aims to map all human 2D pixels to a 3D human template, namely human densepose estimation, involving surface patch recognition (i.e., Index-to-Patch (I)) and regression of patch-specific UV coordinates. Despite recent progress, it remains challenging especially under the condition of in the wild, where RGB images capture real-world scenes with backgrounds, occlusions, scale variations, and postural diversity. In this paper, we address three vital problems in this task: 1) how to perceive multi-scale visual information for instances ‘`in the wild’'; 2) how to design learning objectives to address the precise instance representation harassed by multiple instances in one bounding box phenomenon; and 3) how to boost the performance of index-to-patch prediction faced by limited supervision. To tackle problems above, we propose an end-to-end deep Adaptive Multi-path Aggregation network (AMA-net) for Human DensePose Estimation. First, we introduce an adaptive multi-path aggregation algorithm to extract varying-sized instance-level feature maps, which capture multi-scale information of a bounding-box and are then utilized for analyzing different instances. Second, we adopt an instance augmentation learning objective to further distinguish the target instance from other interference instances. Third, taking advantage of 2D human parsers that are trained from sufficient annotations, we introduce a task transformer that bridges the ‘`gap’' between 2D human parsing and densepose estimation, thus benefiting the performance of densepose estimator. Experimental results on the challenging Dense-COCO dataset demonstrate that our approach sets a new record, and it significantly outperforms the state-of-the-art methods. Codes and models are publicly available.
- 12 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 52 (7) , 5961-5972
Relation Regularized Scene Graph Generation
Scene graph generation (SGG) is built on top of detected objects to predict object pairwise visual relations for describing the image content abstraction. Existing works have revealed that if the links between objects are given as prior knowledge, the performance of SGG is significantly improved. Inspired by this observation, in this article, we propose a relation regularized network (R2-Net), which can predict whether there is a relationship between two objects and encode this relation into object feature refinement and better SGG. Specifically, we first construct an affinity matrix among detected objects to represent the probability of a relationship between two objects. Graph convolution networks (GCNs) over this relation affinity matrix are then used as object encoders, producing relation-regularized representations of objects. With these relation-regularized features, our R2-Net can effectively refine object labels and generate scene graphs. Extensive experiments are conducted on the visual genome dataset for three SGG tasks (i.e., predicate classification, scene graph classification, and scene graph detection), demonstrating the effectiveness of our proposed method. Ablation studies also verify the key roles of our proposed components in performance improvement.
- 12 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 52 (7) , 5961-5972
Relation Regularized Scene Graph Generation
Scene graph generation (SGG) is built on top of detected objects to predict object pairwise visual relations for describing the image content abstraction. Existing works have revealed that if the links between objects are given as prior knowledge, the performance of SGG is significantly improved. Inspired by this observation, in this article, we propose a relation regularized network (R2-Net), which can predict whether there is a relationship between two objects and encode this relation into object feature refinement and better SGG. Specifically, we first construct an affinity matrix among detected objects to represent the probability of a relationship between two objects. Graph convolution networks (GCNs) over this relation affinity matrix are then used as object encoders, producing relation-regularized representations of objects. With these relation-regularized features, our R2-Net can effectively refine object labels and generate scene graphs. Extensive experiments are conducted on the visual genome dataset for three SGG tasks (i.e., predicate classification, scene graph classification, and scene graph detection), demonstrating the effectiveness of our proposed method. Ablation studies also verify the key roles of our proposed components in performance improvement.