Institution profile

Southeast University

Academic institutionasia · cn
Official website
Research library1,778linked papers
Opportunities0open roles
Selected work

Representative Papers

BoostDream: Efficient Refining for High-Quality Text-to-3D Generation from Multi-View Diffusion

Jan 30, 2024International Joint Conference on Artificial Intelligence

To address the longstanding trade-off between quality and efficiency in text-to-3D generation, this paper proposes a plug-and-play, efficient 3D refinement framework that elevates coarse, feedforward-generated 3D assets to high-fidelity levels within seconds. Methodologically, we introduce the first 3D model distillation mechanism, design a multi-view-aware Score Distillation Sampling (SDS) loss, and incorporate joint guidance from normal maps and text prompts—thereby overcoming the “Janus dilemma” of SDS, where geometric accuracy and rendering speed are conventionally at odds. The framework supports diverse differentiable 3D representations—including NeRF and Gaussian Splatting—without requiring retraining. Extensive experiments demonstrate consistent superiority over state-of-the-art baselines across geometric completeness, texture realism, and inference speed, achieving synergistic improvements in both quality and efficiency.

9 citationsRead paper

FocusTrack: One-Stage Focus-and-Suppress Framework for 3D Point Cloud Object Tracking

Oct 27, 2025ACM Multimedia

This work addresses the limitations of existing two-stage 3D point cloud object tracking methods, which rely on explicit foreground segmentation and consequently suffer from error accumulation and computational bottlenecks. To overcome these issues, we propose the first end-to-end single-stage tracking framework that jointly models motion and semantics without explicit segmentation, enabling both efficiency and accuracy. The core innovation lies in a focus-suppression attention mechanism, integrated with a temporal difference Siamese encoder to model inter-frame motion dynamics, thereby adaptively enhancing foreground features while suppressing background noise. Extensive experiments demonstrate that our method achieves state-of-the-art performance on major benchmarks—including KITTI, nuScenes, and Waymo—while running at an impressive inference speed of 105 FPS.

6 citationsRead paper

SOAP: Enhancing Spatio-Temporal Relation and Motion Information Capturing for Few-Shot Action Recognition

Jul 23, 2024ACM Multimedia

To address the challenges of weak spatiotemporal relationships and insufficient motion information density in few-shot action recognition (FSAR) for high-frame-rate (HFR) videos, this paper proposes the Frame-Tuple Augmentation Architecture (SOAP). First, a multi-frame-tuple motion encoder explicitly models dense temporal motion dynamics. Second, a channel-wise temporal connection module jointly optimizes cross-channel temporal dependencies and spatial semantics. Third, a plug-and-play spatiotemporal fusion network—SOAP-Net—enables end-to-end unified modeling. SOAP overcomes two key limitations of conventional FSAR: (1) the decoupling of spatial and temporal features, and (2) reliance on single adjacent-frame motion cues. Extensive experiments demonstrate state-of-the-art performance on SthSthV2, Kinetics, UCF101, and HMDB51, with strong generalization, robustness to frame-rate variations, and seamless integration into existing pipelines.

6 citationsRead paper

Image2Net: Datasets, Benchmark and Hybrid Framework to Convert Analog Circuit Diagrams into Netlists

May 09, 20252025 International Symposium of Electronics Design Automation (ISEDA)

Existing image-to-netlist conversion methods for analog schematics suffer from limited compatibility with diverse schematic styles and insufficient coverage of analog component types. To address these limitations, this paper proposes Image2Net—the first end-to-end framework supporting multi-style, multi-type analog components. Methodologically, it integrates deep learning–driven image recognition and structural parsing, rule-guided topological inference, and semantic consistency verification. We also introduce the first open-source schematic dataset featuring diversity and balanced complexity. Innovatively, we propose Netlist Edit Distance (NED) as a precision metric for quantitative evaluation. Experimental results demonstrate that Image2Net achieves an 80.77% conversion success rate on benchmark tests—surpassing state-of-the-art methods by 34.62–45.19%. Its average NED of 0.116 outperforms existing approaches by 62.1–69.6%, confirming substantial gains in structural and semantic fidelity.

3 citationsRead paper
Recent publications

Latest Papers