Tao Wang

38

Papers

73

Total Citations

Papers (38)

Zero-Shot Aerial Object Detection with Visual Description Regularization

FRIH: Fine-Grained Region-Aware Image Harmonization

VSFormer: Visual-Spatial Fusion Transformer for Correspondence Pruning

HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal Model

Foundations of Top-$k$ Decoding for Language Models

NeurIPS 2025arXiv

A Hubness Perspective on Representation Learning for Graph-Based Multi-View Clustering

StickMotion: Generating 3D Human Motions by Drawing a Stickman

Trend-Aware Supervision: On Learning Invariance for Semi-supervised Facial Action Unit Intensity Estimation

Distilling Object Detectors With Fine-Grained Feature Imitation

Few-Shot Adaptive Faster R-CNN

Central Similarity Quantization for Efficient Image and Video Retrieval

Revisiting Knowledge Distillation via Label Smoothing Regularization

Overcoming Classifier Imbalance for Long-Tail Object Detection With Balanced Group Softmax

Ultra-High-Definition Image Dehazing via Multi-Guided Bilateral Learning

PoseTriplet: Co-Evolving 3D Human Pose Estimation, Imitation, and Hallucination Under Self-Supervision

Learning To Detect and Segment for Open Vocabulary Object Detection

Deformable Surface Tracking by Graph Matching

PnP-DETR: Towards Efficient Visual Analysis With Transformers

End-to-End Video Instance Segmentation via Spatial-Temporal Graph Neural Networks

Tokens-to-Token ViT: Training Vision Transformers From Scratch on ImageNet

Real-Time Image Enhancer via Learnable Spatial-Aware 3D Lookup Tables

Multi-Scale Separable Network for Ultra-High-Definition Video Deblurring

Ultra-High-Definition Image HDR Reconstruction via Collaborative Bilateral Learning

The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation

On Mitigating Hard Clusters for Face Clustering

BézierPalm: A Free Lunch for Palmprint Recognition

Towards Real-World HDRTV Reconstruction: A Data Synthesis-Based Approach

Learning Combinatorial Solver for Graph Matching

MOERL: When Mixture-of-Experts Meet Reinforcement Learning for Adverse Weather Image Restoration

MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion

SALS: Sparse Attention in Latent Space for KV Cache Compression

Rethinking the Representation in Federated Unsupervised Learning with Non-IID Data

SynSP: Synergy of Smoothness and Precision in Pose Sequences Refinement

Mollification Effects of Policy Gradient Methods

Controlled Decoding from Language Models

Rethinking Image Restoration for Object Detection

Fractal Landscapes in Policy Optimization

Punctuation-level Attack: Single-shot and Single Punctuation Can Fool Text Models