Manyuan Zhang

7

Papers

0

Total Citations

Papers (7)

Let's Verify and Reinforce Image Generation Step by Step

FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation

Switchable K-Class Hyperplanes for Noise-Robust Representation Learning

Decoupled DETR: Spatially Disentangling Localization and Classification for Improved End-to-End Object Detection

VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation

Discriminability Distillation in Group Representation Learning

Towards Robust Face Recognition with Comprehensive Search