Shuo Chen

27

Papers

111

Total Citations

Papers (27)

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Decoupled Video Diffusion

BlinkVision: A Benchmark for Optical Flow, Scene Flow and Point Tracking Estimation using RGB Frames and Events

Hybrid Data-Free Knowledge Distillation

Learning Generalized Residual Exchange-Correlation-Uncertain Functional for Density Functional Theory

Modeling Inter-Intra Heterogeneity for Graph Federated Learning

Towards Better Spherical Sliced-Wasserstein Distance Learning with Data-Adaptive Discriminative Projection Direction

On the Unstable Convergence Regime of Gradient Descent

PromptKD: Unsupervised Prompt Distillation for Vision-Language Models

Learning High-Frequency Functions Made Easy with Sinusoidal Positional Encoding

Understanding the Disharmony Between Dropout and Batch Normalization by Variance Shift

Contrastive Embedding for Generalized Zero-Shot Learning

Industrial Style Transfer With Large-Scale Geometric Warping and Content Preservation

PVO: Panoptic Visual Odometry

Social Fabric: Tubelet Compositions for Video Relation Detection

Distribution Shift Matters for Knowledge Distillation with Webly Collected Images

IntrinsicNeRF: Learning Intrinsic Neural Radiance Fields for Editable Novel View Synthesis

Creative Birds: Self-Supervised Single-View 3D Style Transfer

Remote Photoplethysmography in Real-World and Extreme Lighting Scenarios

DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation

BlinkTrack: Feature Tracking over 80 FPS via Events and Images

Curvilinear Distance Metric Learning

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection

Spectrum-to-Kernel Translation for Accurate Blind Image Super-Resolution

Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model

Learning Contrastive Embedding in Low-Dimensional Space

Self-Weighted Contrastive Learning among Multiple Views for Mitigating Representation Degeneration

Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models