ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Huiyu Wang

Huiyu Wang

Topic trends: 31,945 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,180 papers | Abstracts: 30,883 (90.4%) | Citations: 34,180 (100.0%) | arXiv: 25,725 (75.3%)

Built: Feb 4, 2026, 7:44 PM AMS

19

papers

40

total citations

papers (19)

PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding

NeurIPS 2025arXiv

BIMBA: Selective-Scan Compression for Long-Range Video Question Answering

Learning to Segment Referred Objects from Narrated Egocentric Videos

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

MusicFlow: Cascaded Flow Matching for Text Guided Music Generation

MaX-DeepLab: End-to-End Panoptic Segmentation With Mask Transformers

A Simple Data Mixing Prior for Improving Self-Supervised Learning

CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation

TubeFormer-DeepLab: Video Mask Transformer

Masked Autoencoders Enable Efficient Knowledge Distillers

Diffusion Models as Masked Autoencoders

Ego-Only: Egocentric Action Detection without Exocentric Transferring

SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-Training

Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation

In Defense of Image Pre-training for Spatiotemporal Recognition

k-Means Mask Transformer

CP2: Copy-Paste Contrastive Pretraining for Semantic Segmentation

Ego4D Goal-Step: Toward Hierarchical Understanding of Procedural Activities

HT-Step: Aligning Instructional Articles with How-To Videos