Yachao Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yachao Zhang has a total of 66 co-authors. Here are the top co-authors by number of shared publications:
- Yanyun Qu
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China
16 shared publications - Yuan Xie
The Hong Kong University of Science and Technology, Hong Kong, Hong Kong
15 shared publications - Yao Wu
School of Informatics, Xiamen University, Xiamen, China
5 shared publications - Jiangming Shi
School of Computer Science and Technology, East China Normal University, Shanghai, China
3 shared publications - Mingwei Xing
Institute of Artificial Intelligence, Xiamen University, Xiamen, China
3 shared publications - Xiangbo Yin
School of Informatics, Xiamen University, Xiamen, China
3 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 13695-13703
Learning Discriminativity, Compatibility and Adaptivity for Replay-free Lifelong Visible-Infrared Person Re-identification
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 13695-13703
Open AccessLearning Discriminativity, Compatibility and Adaptivity for Replay-free Lifelong Visible-Infrared Person Re-identification
- 30 April 2026
- Published by Elsevier in Pattern Recognition
- Vol. 179
Instructing visual feature modeling with semantic guidance for 3D visual grounding
- 30 April 2026
- Published by Elsevier in Pattern Recognition
- Vol. 179
Instructing visual feature modeling with semantic guidance for 3D visual grounding
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 3094-3103
SeqVLM: Proposal-Guided Multi-View Sequences Reasoning via VLM for Zero-Shot 3D Visual Grounding
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 3094-3103
Open AccessSeqVLM: Proposal-Guided Multi-View Sequences Reasoning via VLM for Zero-Shot 3D Visual Grounding
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 2226-2234
PLATO-TTA: Prototype-Guided Pseudo-Labeling and Adaptive Tuning for Multi-Modal Test-Time Adaptation of 3D Segmentation
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 2226-2234
Open AccessPLATO-TTA: Prototype-Guided Pseudo-Labeling and Adaptive Tuning for Multi-Modal Test-Time Adaptation of 3D Segmentation
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 2929-2938
Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 2929-2938
Open AccessNovel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation
- Top Cited Papers
- 6 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-15
Lodge++: High-Quality and Long Dance Generation With Robust Choreography Patterns
We propose Lodge++, a choreography framework to generate high-quality, ultra-long dances given the music and desired genre. To handle the challenges in computational efficiency, the complex global choreography patterns across various dance genres, and the physical quality of local dance movements, Lodge++ adopts a two-stage strategy to produce dances from coarse to fine. In the first stage, a global choreography network is designed to generate coarse-grained dance primitives that capture complex global choreography patterns. In the second stage, guided by these dance primitives, a primitive-based dance diffusion model is proposed to further generate high-quality, long-sequence dances in parallel, faithfully adhering to the complex choreography patterns. Additionally, to improve the physical plausibility, Lodge++ employs a penetration guidance module to resolve character self-penetration, a foot refinement module to optimize foot-ground contact, and a multi-genre discriminator to maintain genre consistency throughout the dance. Lodge++ is validated by extensive experiments, which show that our method can rapidly generate ultra-long dances suitable for various dance genres, ensuring well-organized global choreography patterns and high-quality local motion. Code, model and demonstrative video results will be available at https://li-ronghui.github.io/lodgepp.
- 6 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-15
Top Cited PapersLodge++: High-Quality and Long Dance Generation With Robust Choreography Patterns
We propose Lodge++, a choreography framework to generate high-quality, ultra-long dances given the music and desired genre. To handle the challenges in computational efficiency, the complex global choreography patterns across various dance genres, and the physical quality of local dance movements, Lodge++ adopts a two-stage strategy to produce dances from coarse to fine. In the first stage, a global choreography network is designed to generate coarse-grained dance primitives that capture complex global choreography patterns. In the second stage, guided by these dance primitives, a primitive-based dance diffusion model is proposed to further generate high-quality, long-sequence dances in parallel, faithfully adhering to the complex choreography patterns. Additionally, to improve the physical plausibility, Lodge++ employs a penetration guidance module to resolve character self-penetration, a foot refinement module to optimize foot-ground contact, and a multi-genre discriminator to maintain genre consistency throughout the dance. Lodge++ is validated by extensive experiments, which show that our method can rapidly generate ultra-long dances suitable for various dance genres, ensuring well-organized global choreography patterns and high-quality local motion. Code, model and demonstrative video results will be available at https://li-ronghui.github.io/lodgepp.
- 26 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (9) , 9030-9045
Fusion-Then-Distillation: Toward Cross-Modal Positive Distillation for Domain Adaptive 3D Semantic Segmentation
In cross-modal unsupervised domain adaptation, a model trained on source-domain data (e.g., synthetic) is adapted to target-domain data (e.g., real-world) without access to target annotation. Previous methods seek to mutually mimic cross-modal outputs in each domain, which enforces a class probability distribution that is agreeable in different domains. However, they overlook the complementarity brought by the heterogeneous fusion in cross-modal learning. In light of this, we propose a novel fusion-then-distillation (FtD++) method to explore cross-modal positive distillation of the source and target domains for 3D semantic segmentation. FtD++ realizes distribution consistency between outputs not only for 2D images and 3D point clouds but also for source-domain and augment-domain. Specially, our method contains three key ingredients. First, we present a model-agnostic feature fusion module to generate the cross-modal fusion representation for establishing a latent space. In this space, two modalities are enforced maximum correlation and complementarity. Second, the proposed cross-modal positive distillation preserves the complete information of multi-modal input and combines the semantic content of the source domain with the style of the target domain, thereby achieving domain-modality alignment. Finally, cross-modal debiased pseudo-labeling is devised to model the uncertainty of pseudo-labels via a self-training manner. Extensive experiments report state-of-the-art results on several domain adaptive scenarios under unsupervised and semi-supervised settings. Code is available at https://github.com/Barcaaaa/FtD-PlusPlus.
- 26 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (9) , 9030-9045
Fusion-Then-Distillation: Toward Cross-Modal Positive Distillation for Domain Adaptive 3D Semantic Segmentation
In cross-modal unsupervised domain adaptation, a model trained on source-domain data (e.g., synthetic) is adapted to target-domain data (e.g., real-world) without access to target annotation. Previous methods seek to mutually mimic cross-modal outputs in each domain, which enforces a class probability distribution that is agreeable in different domains. However, they overlook the complementarity brought by the heterogeneous fusion in cross-modal learning. In light of this, we propose a novel fusion-then-distillation (FtD++) method to explore cross-modal positive distillation of the source and target domains for 3D semantic segmentation. FtD++ realizes distribution consistency between outputs not only for 2D images and 3D point clouds but also for source-domain and augment-domain. Specially, our method contains three key ingredients. First, we present a model-agnostic feature fusion module to generate the cross-modal fusion representation for establishing a latent space. In this space, two modalities are enforced maximum correlation and complementarity. Second, the proposed cross-modal positive distillation preserves the complete information of multi-modal input and combines the semantic content of the source domain with the style of the target domain, thereby achieving domain-modality alignment. Finally, cross-modal debiased pseudo-labeling is devised to model the uncertainty of pseudo-labels via a self-training manner. Extensive experiments report state-of-the-art results on several domain adaptive scenarios under unsupervised and semi-supervised settings. Code is available at https://github.com/Barcaaaa/FtD-PlusPlus.
- 15 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (8) , 14452-14463
Cross-Cloud Consistency for Weakly Supervised Point Cloud Semantic Segmentation
Weakly supervised point cloud semantic segmentation is an increasingly active topic, because fully supervised learning acquires well-labeled point clouds and entails high costs. The existing weakly supervised methods either need meticulously designed data augmentation for self-supervised learning or ignore the negative effects of learning on pseudolabel noises. In this article, by designing different granularity of cross-cloud structures, we propose a cross-cloud consistency method for weakly supervised point cloud semantic segmentation which forms the expectation–maximum (EM) framework. Benefiting from the cross-cloud constraints, our method allows effective learning alternatively between refining pseudolabels and updating network parameters. Specifically, in E-step, we propose a pseudolabel selecting (PLS) strategy based on cross subcloud consistency, improving the credibility of selected pseudolabels explicitly. In M-step, a cross-scene contrastive regularization enforces cross-scene prototypes with the same label in different scenes to be more similar, while keeping prototypes with different labels to be a clear margin, reducing the noise fitting. Finally, we give some insight into the optimization of our method in the EM theoretical way. The proposed method is evaluated on three challenging datasets, where experimental results demonstrate that our method significantly outperforms state-of-the-art weakly supervised competitors. Our code is available online: https://github.com/Yachao-Zhang/Cross-Cloud-Consistency.
- 15 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (8) , 14452-14463
Cross-Cloud Consistency for Weakly Supervised Point Cloud Semantic Segmentation
Weakly supervised point cloud semantic segmentation is an increasingly active topic, because fully supervised learning acquires well-labeled point clouds and entails high costs. The existing weakly supervised methods either need meticulously designed data augmentation for self-supervised learning or ignore the negative effects of learning on pseudolabel noises. In this article, by designing different granularity of cross-cloud structures, we propose a cross-cloud consistency method for weakly supervised point cloud semantic segmentation which forms the expectation–maximum (EM) framework. Benefiting from the cross-cloud constraints, our method allows effective learning alternatively between refining pseudolabels and updating network parameters. Specifically, in E-step, we propose a pseudolabel selecting (PLS) strategy based on cross subcloud consistency, improving the credibility of selected pseudolabels explicitly. In M-step, a cross-scene contrastive regularization enforces cross-scene prototypes with the same label in different scenes to be more similar, while keeping prototypes with different labels to be a clear margin, reducing the noise fitting. Finally, we give some insight into the optimization of our method in the EM theoretical way. The proposed method is evaluated on three challenging datasets, where experimental results demonstrate that our method significantly outperforms state-of-the-art weakly supervised competitors. Our code is available online: https://github.com/Yachao-Zhang/Cross-Cloud-Consistency.
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 2242-2251
Robust Pseudo-label Learning with Neighbor Relation for Unsupervised Visible-Infrared Person Re-Identification
Unsupervised Visible-Infrared Person Re-identification (USVI-ReID) presents a formidable challenge, which aims to match pedestrian images across visible and infrared modalities without any annotations. Recently, clustered pseudo-label methods have become predominant in USVI-ReID, although the inherent noise in pseudo-labels presents a significant obstacle. Most existing works primarily focus on shielding the model from the harmful effects of noise, neglecting to calibrate noisy pseudo-labels usually associated with hard samples, which will compromise the robustness of the model. To address this issue, we design a Robust Pseudo-label Learning with Neighbor Relation (RPNR) framework for USVI-ReID. To be specific, we first introduce a straightforward yet potent Noisy Pseudo-label Calibration module to correct noisy pseudo-labels. Due to the high intra-class variations, noisy pseudo-labels are difficult to calibrate completely. Therefore, we introduce a Neighbor Relation Learning module to reduce high intra-class variations by modeling potential interactions between all samples. Subsequently, we devise an Optimal Transport Prototype Matching module to establish reliable cross-modality correspondences. On that basis, we design a Memory Hybrid Learning module to jointly learn modality-specific and modality-invariant information. Comprehensive experiments conducted on two widely recognized benchmarks, SYSU-MM01 and RegDB, demonstrate that RPNR outperforms the current state-of-the-art GUR with an average Rank-1 improvement of 10.3%. The code is available at https://github.com/XiangboYin/RPNR.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 2242-2251
Open AccessRobust Pseudo-label Learning with Neighbor Relation for Unsupervised Visible-Infrared Person Re-Identification
Unsupervised Visible-Infrared Person Re-identification (USVI-ReID) presents a formidable challenge, which aims to match pedestrian images across visible and infrared modalities without any annotations. Recently, clustered pseudo-label methods have become predominant in USVI-ReID, although the inherent noise in pseudo-labels presents a significant obstacle. Most existing works primarily focus on shielding the model from the harmful effects of noise, neglecting to calibrate noisy pseudo-labels usually associated with hard samples, which will compromise the robustness of the model. To address this issue, we design a Robust Pseudo-label Learning with Neighbor Relation (RPNR) framework for USVI-ReID. To be specific, we first introduce a straightforward yet potent Noisy Pseudo-label Calibration module to correct noisy pseudo-labels. Due to the high intra-class variations, noisy pseudo-labels are difficult to calibrate completely. Therefore, we introduce a Neighbor Relation Learning module to reduce high intra-class variations by modeling potential interactions between all samples. Subsequently, we devise an Optimal Transport Prototype Matching module to establish reliable cross-modality correspondences. On that basis, we design a Memory Hybrid Learning module to jointly learn modality-specific and modality-invariant information. Comprehensive experiments conducted on two widely recognized benchmarks, SYSU-MM01 and RegDB, demonstrate that RPNR outperforms the current state-of-the-art GUR with an average Rank-1 improvement of 10.3%. The code is available at https://github.com/XiangboYin/RPNR.