Guang Dai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Guang Dai has a total of 98 co-authors. Here are the top co-authors by number of shared publications:
- Jingdong Wang
Baidu, Beijing, China
17 shared publications - Mengmeng Wang
Zhejiang University of Technology
15 shared publications - Yong Liu
Zhejiang University
11 shared publications - Minnan Luo
Xi'an Jiaotong University, Xi'an, China
8 shared publications - Ivor W. Tsang
College of Computing and Data Science, Nanyang Technological University, Singapore, Singapore
7 shared publications - Jun Chen
National Special Education Resource Center for Children with Autism, Zhejiang Normal University, Hangzhou, 311231, China; School of Computer Science and Technology, Zhejiang Normal University, Jinhua, 321004, China
5 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3727-3736
AffordanceSAM: Segment Anything Once More in Affordance Grounding
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3727-3736
Open AccessAffordanceSAM: Segment Anything Once More in Affordance Grounding
- 24 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control of Network Systems
- Vol. 13 (2) , 970-979
Riemannian Momentum Tracking: Distributed Optimization With Momentum on Compact Submanifolds
Gradient descent with momentum has been widely applied in various signal processing and machine learning tasks, demonstrating a notable empirical advantage over standard gradient descent. However, momentum-based distributed Riemannian algorithms have been only scarcely explored. In this paper, we propose Riemannian Momentum Tracking (RMTracking), a decentralized optimization algorithm with momentum over a compact submanifold. Given the non-convex nature of compact submanifolds, the objective function, composed of a finite sum of smooth (possibly non-convex) local functions, is minimized across agents in an undirected and connected network graph. With a constant step-size, we establish an $\mathcal {O}(\frac{1-\beta }{K})$ convergence rate of the Riemannian gradient average for any momentum weight $\beta \in [0,1)$. Especially, RMTracking can achieve a convergence rate of $\mathcal {O}(\frac{1-\beta }{K})$ to a stationary point when the step-size is sufficiently small. To best of our knowledge, RMTracking is the first decentralized algorithm to achieve exact convergence that is $\frac{1}{1-\beta }$ times faster than other related algorithms. Finally, we verify these theoretical claims through numerical experiments on eigenvalue problems.
- 24 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control of Network Systems
- Vol. 13 (2) , 970-979
Riemannian Momentum Tracking: Distributed Optimization With Momentum on Compact Submanifolds
Gradient descent with momentum has been widely applied in various signal processing and machine learning tasks, demonstrating a notable empirical advantage over standard gradient descent. However, momentum-based distributed Riemannian algorithms have been only scarcely explored. In this paper, we propose Riemannian Momentum Tracking (RMTracking), a decentralized optimization algorithm with momentum over a compact submanifold. Given the non-convex nature of compact submanifolds, the objective function, composed of a finite sum of smooth (possibly non-convex) local functions, is minimized across agents in an undirected and connected network graph. With a constant step-size, we establish an $\mathcal {O}(\frac{1-\beta }{K})$ convergence rate of the Riemannian gradient average for any momentum weight $\beta \in [0,1)$. Especially, RMTracking can achieve a convergence rate of $\mathcal {O}(\frac{1-\beta }{K})$ to a stationary point when the step-size is sufficiently small. To best of our knowledge, RMTracking is the first decentralized algorithm to achieve exact convergence that is $\frac{1}{1-\beta }$ times faster than other related algorithms. Finally, we verify these theoretical claims through numerical experiments on eigenvalue problems.
- 29 January 2026
- Published by Elsevier in Neural Networks
- Vol. 199, 108647
Warm-start or cold-start? A comparison of generalizability in gradient-based hyperparameter tuning
- 29 January 2026
- Published by Elsevier in Neural Networks
- Vol. 199, 108647
Warm-start or cold-start? A comparison of generalizability in gradient-based hyperparameter tuning
- Open Access
- 18 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-5
VisualNetO&M: A Digital Twin-Based Collaborative Visualization System for Power System Communication Network Operation and Maintenance
- 18 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessVisualNetO&M: A Digital Twin-Based Collaborative Visualization System for Power System Communication Network Operation and Maintenance
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 9216-9225
Understand, Refine and Summarize: Multi-View Knowledge Progressive Enhancement Learning for Fake News Video Detection
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 9216-9225
Open AccessUnderstand, Refine and Summarize: Multi-View Knowledge Progressive Enhancement Learning for Fake News Video Detection
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 5257-5266
TriCLIP-3D: A Unified Parameter-Efficient Framework for Tri-Modal 3D Visual Grounding based on CLIP
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 5257-5266
Open AccessTriCLIP-3D: A Unified Parameter-Efficient Framework for Tri-Modal 3D Visual Grounding based on CLIP
- Open Access
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 1, 747-755
Instructing Text-to-Image Diffusion Models via Classifier-Guided Semantic Optimization
Text-to-image diffusion models have emerged as powerful tools for high-quality image generation and editing. Many existing approaches rely on text prompts as editing guidance. However, these methods are constrained by the need for manual prompt crafting, which can be time-consuming, introduce irrelevant details, and significantly limit editing performance. In this work, we propose optimizing semantic embeddings guided by attribute classifiers to steer text-to-image models toward desired edits, without relying on text prompts or requiring any training or fine-tuning of the diffusion model. We utilize classifiers to learn precise semantic embeddings at the dataset level. The learned embeddings are theoretically justified as the optimal representation of attribute semantics, enabling disentangled and accurate edits. Experiments further demonstrate that our method achieves high levels of disentanglement and strong generalization across different domains of data. Code is available at https://github.com/Chang-yuanyuan/CASO.
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 1, 747-755
Open AccessInstructing Text-to-Image Diffusion Models via Classifier-Guided Semantic Optimization
Text-to-image diffusion models have emerged as powerful tools for high-quality image generation and editing. Many existing approaches rely on text prompts as editing guidance. However, these methods are constrained by the need for manual prompt crafting, which can be time-consuming, introduce irrelevant details, and significantly limit editing performance. In this work, we propose optimizing semantic embeddings guided by attribute classifiers to steer text-to-image models toward desired edits, without relying on text prompts or requiring any training or fine-tuning of the diffusion model. We utilize classifiers to learn precise semantic embeddings at the dataset level. The learned embeddings are theoretically justified as the optimal representation of attribute semantics, enabling disentangled and accurate edits. Experiments further demonstrate that our method achieves high levels of disentanglement and strong generalization across different domains of data. Code is available at https://github.com/Chang-yuanyuan/CASO.
- Open Access
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 1, 882-890
VidEvo: Evolving Video Editing through Exhaustive Temporal Modeling
Text-guided video editing (TGVE) has become a recent hotspot due to its entertainment value and practical applications. To reduce overhead, existing methods primarily extend from text-to-image diffusion models and typically involve reconstruction and editing phases. However, challenges persist, particularly in enhancing temporal consistency of a video while adhering to textual alignment requirements. A crucial factor leading to the aforementioned issue is the inadequate and implicit tuning of the attention module within existing methods, which is specifically designed to capture temporal information. In light of this, we introduce VidEvo, a novel one-shot video editing method that leverages explicit cues derived from the original video to enhance temporal modeling. By integrating null-video embedding (NVE) and window-frame attention (WFA) components, VidEvo facilitates the smooth and coherent generation of videos from global and local perspectives simultaneously. To be specific, NVE learns a set of multi-scale temporal embeddings within the visual space during the reconstruction phase. These embeddings are subsequently directly injected into the attention module of the editing phase, explicitly augmenting the temporal consistency of the entire video. On the other hand, WFA enhances local temporal modeling by dynamically optimizing attention mechanisms between adjacent frames, which improves temporal coherence with reduced computational costs. Experimental evaluations show that VidEvo enhances frame-to-frame temporal consistency. Ablation studies confirm NVE and WFA’s effectiveness and their plug-and-play capability with other methods.
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 1, 882-890
Open AccessVidEvo: Evolving Video Editing through Exhaustive Temporal Modeling
Text-guided video editing (TGVE) has become a recent hotspot due to its entertainment value and practical applications. To reduce overhead, existing methods primarily extend from text-to-image diffusion models and typically involve reconstruction and editing phases. However, challenges persist, particularly in enhancing temporal consistency of a video while adhering to textual alignment requirements. A crucial factor leading to the aforementioned issue is the inadequate and implicit tuning of the attention module within existing methods, which is specifically designed to capture temporal information. In light of this, we introduce VidEvo, a novel one-shot video editing method that leverages explicit cues derived from the original video to enhance temporal modeling. By integrating null-video embedding (NVE) and window-frame attention (WFA) components, VidEvo facilitates the smooth and coherent generation of videos from global and local perspectives simultaneously. To be specific, NVE learns a set of multi-scale temporal embeddings within the visual space during the reconstruction phase. These embeddings are subsequently directly injected into the attention module of the editing phase, explicitly augmenting the temporal consistency of the entire video. On the other hand, WFA enhances local temporal modeling by dynamically optimizing attention mechanisms between adjacent frames, which improves temporal coherence with reduced computational costs. Experimental evaluations show that VidEvo enhances frame-to-frame temporal consistency. Ablation studies confirm NVE and WFA’s effectiveness and their plug-and-play capability with other methods.
- Open Access
Decentralized Optimization on Compact Submanifolds by Quantized Riemannian Gradient Tracking
This paper considers the problem of decentralized optimization on compact submanifolds, where a finite sum of smooth (possibly non-convex) local functions is minimized by $n$ agents forming an undirected and connected graph. However, the efficiency of distributed optimization is often hindered by communication bottlenecks. To mitigate this, we propose the Quantized Riemannian Gradient Tracking (Q-RGT) algorithm, where agents update their local variables using quantized gradients. The introduction of quantization noise allows our algorithm to bypass the constraints of the accurate Riemannian projection operator (such as retraction), further improving iterative efficiency. To the best of our knowledge, this is the first algorithm to achieve an $\mathcal{O}(1/K)$ convergence rate in the presence of quantization, matching the convergence rate of methods without quantization. Additionally, we explicitly derive lower bounds on decentralized consensus associated with a function of quantization levels. Numerical experiments demonstrate that Q-RGT performs comparably to non-quantized methods while reducing communication bottlenecks and computational overhead.Open AccessDecentralized Optimization on Compact Submanifolds by Quantized Riemannian Gradient Tracking
This paper considers the problem of decentralized optimization on compact submanifolds, where a finite sum of smooth (possibly non-convex) local functions is minimized by $n$ agents forming an undirected and connected graph. However, the efficiency of distributed optimization is often hindered by communication bottlenecks. To mitigate this, we propose the Quantized Riemannian Gradient Tracking (Q-RGT) algorithm, where agents update their local variables using quantized gradients. The introduction of quantization noise allows our algorithm to bypass the constraints of the accurate Riemannian projection operator (such as retraction), further improving iterative efficiency. To the best of our knowledge, this is the first algorithm to achieve an $\mathcal{O}(1/K)$ convergence rate in the presence of quantization, matching the convergence rate of methods without quantization. Additionally, we explicitly derive lower bounds on decentralized consensus associated with a function of quantization levels. Numerical experiments demonstrate that Q-RGT performs comparably to non-quantized methods while reducing communication bottlenecks and computational overhead.