Qixiang Ye

53

Papers

748

Total Citations

Papers (53)

Prototype Mixture Models for Few-shot Semantic Segmentation

Multiple Expert Brainstorming for Domain Adaptive Person Re-identification

Adaptive Keyframe Sampling for Long Video Understanding

Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection

DynRefer: Delving into Region-level Multimodal Tasks via Dynamic Resolution

ChatterBox: Multimodal Referring and Grounding with Chain-of-Questions

Kepler codebook

Self-Learning Scene-Specific Pedestrian Detectors Using a Progressive Latent Model

Oriented Response Networks

SRN: Side-output Residual Network for Object Symmetry Detection in the Wild

Image-Image Domain Adaptation With Preserved Self-Similarity and Domain-Dissimilarity for Person Re-Identification

Min-Entropy Latent Model for Weakly Supervised Object Detection

Weakly Supervised Instance Segmentation Using Class Peak Response

SIXray: A Large-Scale Security Inspection X-Ray Benchmark for Prohibited Item Discovery in Overlapping Images

C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection

Towards Optimal Structured CNN Pruning via Generative Adversarial Learning

Learning Instance Activation Maps for Weakly Supervised Instance Segmentation

Orthogonal Decomposition Network for Pixel-Wise Binary Classification

Cogradient Descent for Bilinear Optimization

Video Playback Rate Perception for Self-Supervised Spatio-Temporal Representation Learning

AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-Identification

Rethinking Performance Estimation in Neural Architecture Search

Multiple Anchor Learning for Visual Object Detection

Beyond Bounding-Box: Convex-Hull Feature Adaptation for Oriented and Densely Packed Object Detection

Towards Compact CNNs via Collaborative Compression

Anti-Aliasing Semantic Reconstruction for Few-Shot Semantic Segmentation

Multiple Instance Active Learning for Object Detection

Beyond Max-Margin: Class Margin Equilibrium for Few-Shot Object Detection

Object Localization Under Single Coarse Point Supervision

Multi-Agent Automated Machine Learning

Integrally Pre-Trained Transformer Pyramid Networks

Generic-to-Specific Distillation of Masked Autoencoders

Soft Proposal Networks for Weakly Supervised Object Localization

DANet: Divergent Activation for Weakly Supervised Object Localization

Selective Sparse Sampling for Fine-Grained Image Recognition

Architecture Disentanglement for Deep Neural Networks

Self-Motivated Communication Agent for Real-World Vision-Dialog Navigation

Occlude Them All: Occlusion-Aware Attention Network for Occluded Person Re-ID

TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization

Generative Prompt Model for Weakly Supervised Object Localization

Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection

Component Divide-and-Conquer for Real-World Image Super-Resolution

API-Net: Robust Generative Classifier via a Single Discriminator

Point-to-Box Network for Accurate Object Detection via Single Point Supervision

End-to-End Weakly Supervised Object Detection with Sparse Proposal Evolution

Conformer: Local Features Coupling Global Representations for Visual Recognition

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model

Building Vision Models upon Heat Conduction

RS-vHeat: Heat Conduction Guided Efficient Remote Sensing Foundation Model

Spatial Transform Decoupling for Oriented Object Detection

Regressor-Segmenter Mutual Prompt Learning for Crowd Counting

FreeAnchor: Learning to Match Anchors for Visual Object Detection

Information Competing Process for Learning Diversified Representations