Yifei Huang

papers

2,769

total citations

papers (22)

Ego4D: Around the World in 3,000 Hours of Egocentric Video

CVPR 2022arXiv

1,511

citations

Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives

CVPR 2024arXiv

343

citations

EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World

CVPR 2024arXiv

citations

Memory-and-Anticipation Transformer for Online Action Understanding

ICCV 2023arXiv

citations

Compound Prototype Matching for Few-Shot Action Recognition

ECCV 2022arXiv

citations

Retrieval-Augmented Egocentric Video Captioning

CVPR 2024arXiv

citations

CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding

ICLR 2025arXiv

citations

Structural Multiplane Image: Bridging Neural View Synthesis and 3D Reconstruction

CVPR 2023arXiv

citations

Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning

ICLR 2025arXiv

citations

EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs

NEURIPS 2025arXiv

citations

ActionVOS: Actions as Prompts for Video Object Segmentation

ECCV 2024arXiv

citations

Learning Streaming Video Representation via Multitask Training

ICCV 2025arXiv

citations

TextCenGen: Attention-Guided Text-Centric Background Adaptation for Text-to-Image Generation

ICML 2025arXiv

citations

Beyond Label Semantics: Language-Guided Action Anatomy for Few-shot Action Recognition

ICCV 2025arXiv

citations

Egocentric Action-aware Inertial Localization in Point Clouds with Vision-Language Guidance

ICCV 2025arXiv

citations

Learn to Recover Visible Color for Video Surveillance in a Day

ECCV 2020

citations

Improving Action Segmentation via Graph-Based Temporal Reasoning

CVPR 2020

citations

Weakly Supervised Temporal Sentence Grounding With Uncertainty-Guided Self-Training

CVPR 2023

citations

Interact Before Align: Leveraging Cross-Modal Knowledge for Domain Adaptive Action Recognition

CVPR 2022

citations

Yifei Huang

papers (22)

Ego4D: Around the World in 3,000 Hours of Egocentric Video

Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives

CLRNet: Cross Layer Refinement Network for Lane Detection

Goal-Oriented Gaze Estimation for Zero-Shot Learning

FACIAL: Synthesizing Dynamic Talking Face With Implicit Attribute Learning

EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World

Memory-and-Anticipation Transformer for Online Action Understanding

Compound Prototype Matching for Few-Shot Action Recognition

Retrieval-Augmented Egocentric Video Captioning

CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding

Structural Multiplane Image: Bridging Neural View Synthesis and 3D Reconstruction

Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning

EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs

ActionVOS: Actions as Prompts for Video Object Segmentation

Learning Streaming Video Representation via Multitask Training

TextCenGen: Attention-Guided Text-Centric Background Adaptation for Text-to-Image Generation

Beyond Label Semantics: Language-Guided Action Anatomy for Few-shot Action Recognition

Egocentric Action-aware Inertial Localization in Point Clouds with Vision-Language Guidance

Learn to Recover Visible Color for Video Surveillance in a Day

Improving Action Segmentation via Graph-Based Temporal Reasoning

Weakly Supervised Temporal Sentence Grounding With Uncertainty-Guided Self-Training

Interact Before Align: Leveraging Cross-Modal Knowledge for Domain Adaptive Action Recognition

papers (22)

Ego4D: Around the World in 3,000 Hours of Egocentric Video

Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives

CLRNet: Cross Layer Refinement Network for Lane Detection

Goal-Oriented Gaze Estimation for Zero-Shot Learning

FACIAL: Synthesizing Dynamic Talking Face With Implicit Attribute Learning

EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World

Memory-and-Anticipation Transformer for Online Action Understanding

Compound Prototype Matching for Few-Shot Action Recognition

Retrieval-Augmented Egocentric Video Captioning

CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding

Structural Multiplane Image: Bridging Neural View Synthesis and 3D Reconstruction

Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning

EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs

ActionVOS: Actions as Prompts for Video Object Segmentation

Learning Streaming Video Representation via Multitask Training

TextCenGen: Attention-Guided Text-Centric Background Adaptation for Text-to-Image Generation

Beyond Label Semantics: Language-Guided Action Anatomy for Few-shot Action Recognition

Egocentric Action-aware Inertial Localization in Point Clouds with Vision-Language Guidance

Learn to Recover Visible Color for Video Surveillance in a Day

Improving Action Segmentation via Graph-Based Temporal Reasoning

Weakly Supervised Temporal Sentence Grounding With Uncertainty-Guided Self-Training

Interact Before Align: Leveraging Cross-Modal Knowledge for Domain Adaptive Action Recognition