ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Peng Dai

Peng Dai

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 16, 2026, 4:10 AM AMS

20

papers

562

total citations

papers (20)

Learning a Proposal Classifier for Multiple Object Tracking

Neural Point Cloud Rendering via Multi-Plane Projection

Boosting the Generalization Capability in Cross-Domain Few-Shot Learning via Noise-Enhanced Supervised Autoencoder

Class Semantics-Based Attention for Action Detection

Texture Generation on 3D Meshes with Point-UV Diffusion

Video Demoireing With Relation-Based Temporal Consistency

Hybrid Neural Rendering for Large-Scale Scenes With Motion Blur

HMD-Poser: On-Device Real-time Human Motion Tracking from Scalable Sparse Observations

Learning a Room with the Occ-SDF Hybrid: Signed Distance Function Mingled with Occupancy Aids Scene Representation

SVG: 3D Stereoscopic Video Generation via Denoising Frame Matrix

Total-Decom: Decomposed 3D Scene Reconstruction with Minimal Interaction

EMHI: A Multimodal Egocentric Human Motion Dataset with HMD and Body-Worn IMUs

Weight Excitation: Built-in Attention Mechanisms in Convolutional Neural Networks

Decorate3D: Text-Driven High-Quality Texture Generation for Mesh Decoration in the Wild

CL-NeRF: Continual Learning of Neural Radiance Fields for Evolving Scene Representation

Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoiréing

Dual Perspective Network for Audio-Visual Event Localization

CLIPPING: Distilling CLIP-Based Models With a Student Base for Video-Language Retrieval

Towards Efficient Coarse-to-Fine Networks for Action and Gesture Recognition

HiVLP: Hierarchical Interactive Video-Language Pre-Training