Yue Liao

papers

1,684

total citations

papers (16)

PPDM: Parallel Point Detection and Matching for Real-Time Human-Object Interaction Detection

CVPR 2020arXiv

314

citations

A Real-Time Cross-Modality Correlation Filtering Method for Referring Expression Comprehension

CVPR 2020arXiv

239

citations

Mining the Benefits of Two-stage and One-stage HOI Detection

NEURIPS 2021arXiv

194

citations

GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection

CVPR 2022arXiv

187

citations

VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection

CVPR 2025arXiv

citations

Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology

ICLR 2025arXiv

citations

Video Background Music Generation: Dataset, Method and Evaluation

ICCV 2023arXiv

citations

From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning

ICCV 2025arXiv

citations

HEAD: HEtero-Assists Distillation for Heterogeneous Object Detectors

ECCV 2022arXiv

citations

Mixture Compressor for Mixture-of-Experts LLMs Gains More

ICLR 2025arXiv

citations

UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning

NEURIPS 2025arXiv

citations

Instruction-Oriented Preference Alignment for Enhancing Multi-Modal Comprehension Capability of MLLMs

ICCV 2025arXiv

citations

Yue Liao

papers (16)

PPDM: Parallel Point Detection and Matching for Real-Time Human-Object Interaction Detection

A Real-Time Cross-Modality Correlation Filtering Method for Referring Expression Comprehension

Mining the Benefits of Two-stage and One-stage HOI Detection

GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection

Reformulating HOI Detection As Adaptive Set Prediction

CentripetalNet: Pursuing High-Quality Keypoint Pairs for Object Detection

Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection

Local Correlation Consistency for Knowledge Distillation

VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection

Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology

Video Background Music Generation: Dataset, Method and Evaluation

From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning

HEAD: HEtero-Assists Distillation for Heterogeneous Object Detectors

Mixture Compressor for Mixture-of-Experts LLMs Gains More

UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning

Instruction-Oriented Preference Alignment for Enhancing Multi-Modal Comprehension Capability of MLLMs

papers (16)

PPDM: Parallel Point Detection and Matching for Real-Time Human-Object Interaction Detection

A Real-Time Cross-Modality Correlation Filtering Method for Referring Expression Comprehension

Mining the Benefits of Two-stage and One-stage HOI Detection

GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection

Reformulating HOI Detection As Adaptive Set Prediction

CentripetalNet: Pursuing High-Quality Keypoint Pairs for Object Detection

Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection

Local Correlation Consistency for Knowledge Distillation

VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection

Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology

Video Background Music Generation: Dataset, Method and Evaluation

From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning

HEAD: HEtero-Assists Distillation for Heterogeneous Object Detectors

Mixture Compressor for Mixture-of-Experts LLMs Gains More

UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning

Instruction-Oriented Preference Alignment for Enhancing Multi-Modal Comprehension Capability of MLLMs