Feng Zhu

32

Papers

3

Total Citations

Papers (32)

Re-Aligning Language to Visual Objects with an Agentic Workflow

Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions

Learning Spatial Regularization With Image-Level Supervisions for Multi-Label Image Classification

Attention-Aware Compositional Network for Person Re-Identification

Towards Unified INT8 Training for Convolutional Neural Network

Feature Erasing and Diffusion Network for Occluded Person Re-Identification

Learning Memory-Augmented Unidirectional Metrics for Cross-Modality Person Re-Identification

Align Representations With Base: A New Approach to Self-Supervised Learning

Revisiting the Transferability of Supervised Pretraining: An MLP Perspective

CORA: Adapting CLIP for Open-Vocabulary Detection With Region Prompting and Anchor Pre-Matching

UniHCP: A Unified Model for Human-Centric Perceptions

HumanBench: Towards General Human-Centric Perception With Projector Assisted Pretraining

MixMix: All You Need for Data-Free Compression Are Feature and Data Mixing

Progressive Correspondence Pruning by Consensus Learning

Human Preference Score: Better Aligning Text-to-Image Models with Human Preference

Locating Noise is Halfway Denoising for Semi-Supervised Segmentation

Advancing Referring Expression Segmentation Beyond Single Image

CORE: Co-planarity Regularized Monocular Geometry Estimation with Weak Supervision

Self-supervising Fine-grained Region Similarities for Large-scale Image Localization

Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification

Unifying Visual Contrastive Learning for Object Recognition from a Graph Perspective

Relative Contrastive Loss for Unsupervised Representation Learning

Instance As Identity: A Generic Online Paradigm for Video Instance Segmentation

Domain Invariant Masked Autoencoders for Self-Supervised Learning from Multi-Domains

Diffusion Transformer meets Multi-level Wavelet Spectrum for Single Image Super-Resolution

Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID

Deep inference of latent dynamics with spatio-temporal super-resolution using selective backpropagation through time

Debiased Causal Tree: Heterogeneous Treatment Effects Estimation with Unmeasured Confounding

Unsupervised Object Detection Pretraining with Joint Object Priors Generation and Detector Learning

A Simple and Optimal Policy Design for Online Learning with Safety against Heavy-tailed Risk

Stochastic Multi-armed Bandits: Optimal Trade-off among Optimality, Consistency, and Tail Risk

Described Object Detection: Liberating Object Detection with Flexible Expressions