ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Xiaoming Wei

Xiaoming Wei

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 14, 2026, 11:22 PM AMS

15

papers

839

total citations

papers (15)

Rethinking BiSeNet for Real-Time Semantic Segmentation

Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation

LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding

Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation

NEURIPS 2025arXiv

Unleashing the Temporal-Spatial Reasoning Capacity of GPT for Training-Free Audio and Language Referenced Video Object Segmentation

ODM: A Text-Image Further Alignment Pre-training Approach for Scene Text Detection and Spotting

BEM: Balanced and Entropy-based Mix for Long-Tailed Semi-Supervised Learning

ARIG: Autoregressive Interactive Head Generation for Real-time Conversations

Animating General Image with Large Visual Motion Model

Masked Auto-Encoders Meet Generative Adversarial Networks and Beyond

Real3D the Curious Case of Neural Scene Degeneration

Embedded Discriminative Attention Mechanism for Weakly Supervised Semantic Segmentation

Bridging Search Region Interaction With Template for RGB-T Tracking

Adaptive Spatial-BCE Loss for Weakly Supervised Semantic Segmentation

Elastic Aggregation for Federated Optimization