Bing Su

22

Papers

21

Total Citations

Papers (22)

STOP: Integrated Spatial-Temporal Dynamic Prompting for Video Understanding

DenoiseVAE: Learning Molecule-Adaptive Noise Distributions for Denoising-based 3D Molecular Pre-training

Regulatory DNA Sequence Design with Reinforcement Learning

Towards the Causal Complete Cause of Multi-Modal Representation Learning

Rethinking the Bias of Foundation Model under Long-tailed Distribution

Heteroscedastic Max-Min Distance Analysis

Order-Preserving Wasserstein Distance for Sequence Matching

Online Joint Multi-Metric Adaptation From Frequent Sharing-Subset Mining for Person Re-Identification

Transfer Knowledge From Head to Tail: Uncertainty Calibration Under Long-Tailed Distribution

Modeling Video As Stochastic Processes for Fine-Grained Video Representation Learning

Order-Preserving Wasserstein Discriminant Analysis

Exploring Temporal Concurrency for Video-Language Representation Learning

Easy Identification From Better Constraints: Multi-Shot Person Re-Identification From Reference Constraints

Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image Alignment

A Plug-and-Play Bregman ADMM Module for Inferring Event Branches in Temporal Point Processes

Dynamic Prompt Optimizing for Text-to-Image Generation

Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-training

Log-Polar Space Convolution Layers

SemMAE: Semantic-Guided Masking for Learning Masked Autoencoders

MetaMask: Revisiting Dimensional Confounder for Self-Supervised Learning

Learning Low-Dimensional Temporal Representations

Learning Distance for Sequences by Learning a Ground Metric