Qibin Hou

35

Papers

165

Total Citations

Papers (35)

DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation

Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation

TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes

Docopilot: Improving Multimodal Models for Document-Level Understanding

Unbiased Region-Language Alignment for Open-Vocabulary Dense Prediction

TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs

KAC: Kolmogorov-Arnold Classifier for Continual Learning

Re-Aligning Language to Visual Objects with an Agentic Workflow

Traffic Scene Parsing through the TSP6K Dataset

Multi-Task Dense Prediction via Mixture of Low-Rank Experts

Deeply Supervised Salient Object Detection With Short Connections

A Simple Pooling-Based Design for Real-Time Salient Object Detection

S4Net: Single Stage Salient-Instance Segmentation

Strip Pooling: Rethinking Spatial Pooling for Scene Parsing

Improving Convolutional Networks With Self-Calibrated Convolutions

Coordinate Attention for Efficient Mobile Network Design

Localization Distillation for Dense Object Detection

L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation

AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation

Integral Object Mining via Online Attention Accumulation

AutoSpace: Neural Architecture Search With Less Human Interference

Large Selective Kernel Network for Remote Sensing Object Detection

SRFormer: Permuted Self-Attention for Single Image Super-Resolution

Rethinking Bottleneck Structure for Efficient Mobile Network Design

DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation

K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAs

TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction

Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignment

AR-1-to-3: Single Image to Consistent 3D Object via Next-View Prediction

Polyper: Boundary Sensitive Polyp Segmentation

CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation

CrossKD: Cross-Head Knowledge Distillation for Object Detection

Self-Erasing Network for Integral Object Attention

All Tokens Matter: Token Labeling for Training Better Vision Transformers

SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation