Yazhou Yao

21

Papers

25

Total Citations

Papers (21)

VideoMAC: Video Masked Autoencoders Meet ConvNets

Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection

CA2C: A Prior-Knowledge-Free Approach for Robust Label Noise Learning via Asymmetric Co-learning and Co-training

Cycle-Consistent Learning for Joint Layout-to-Image Generation and Object Detection

Tensor-aggregated LoRA in Federated Fine-tuning

3D-aware Select, Expand, and Squeeze Token for Aerial Action Recognition

Twofold Debiasing Enhances Fine-Grained Learning with Coarse Labels

Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning

Poly Kernel Inception Network for Remote Sensing Detection

Attentive Region Embedding Network for Zero-Shot Learning

Jo-SRC: A Contrastive Approach for Combating Noisy Labels

Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation

PNP: Robust Learning From Noisy Labels by Probabilistic Noise Prediction

SegEQA: Video Segmentation Based Visual Attention for Embodied Question Answering

Webly Supervised Fine-Grained Recognition: Benchmark Datasets and an Approach

Few-Shot Semantic Segmentation With Cyclic Memory Network

Region Graph Embedding Network for Zero-Shot Learning

Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation

UNIALIGN: Scaling Multimodal Alignment within One Unified Model

Exploiting Frequency Dynamics for Enhanced Multimodal Event-based Action Recognition

Field-wise Learning for Multi-field Categorical Data