← authors · overview

• Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition
  2022 · 73 citations
• Semantic Edge Detection with Diverse Deep Supervision
  2018 · 40 citations
• An Evaluation of Feature Matchers for Fundamental Matrix Estimation
  2019 · 38 citations
• YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection
  2023 · 23 citations
• Three Birds One Stone: A General Architecture for Salient Object Segmentation, Edge Detection and Skeleton Extraction
  2018 · 11 citations
• Optimizing the F-measure for Threshold-free Salient Object Detection
  2018 · 11 citations
• P2T: Pyramid Pooling Transformer for Scene Understanding
  2021 · 11 citations
• Towards An End-to-End Framework for Flow-Guided Video Inpainting
  2022 · 10 citations
• Contrastive Masked Autoencoders are Stronger Vision Learners
  2022 · 8 citations
• Bottom-Up Top-Down Cues for Weakly-Supervised Semantic Segmentation
  2016 · 4 citations
• Centralized Information Interaction for Salient Object Detection
  2020 · 4 citations
• Dual Pyramid Generative Adversarial Networks for Semantic Image Synthesis
  2022 · 4 citations
• Class Incremental Learning with Pre-trained Vision-Language Models
  2023 · 3 citations
• Attention Debiasing for Token Pruning in Vision Language Models
  2025 · 2 citations
• S4Net: Single Stage Salient-Instance Segmentation
  2017 · 2 citations