Zhiheng Li

14

Papers

41

Total Citations

Papers (14)

Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset

Discover and Mitigate Multiple Biased Subgroups in Image Classifiers

LOMA: Language-assisted Semantic Occupancy Network via Triplane Mamba

Learning Dual-Level Deformable Implicit Representation for Real-World Scale Arbitrary Super-Resolution

UAV-Human: A Large Benchmark for Human Behavior Understanding With Unmanned Aerial Vehicles

StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesis

A Whac-a-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others

Discover the Unknown Biased Attribute of an Image Classifier

Skip-Plan: Procedure Planning in Instructional Videos via Condensed Action Space Learning

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

Discover and Mitigate Unknown Biases with Debiasing Alternate Networks

FairRAG: Fair Human Generation via Fair Retrieval Augmentation

Deep Grouping Model for Unified Perceptual Parsing

Learning a Weakly-Supervised Video Actor-Action Segmentation Model With a Wise Selection