Cheng Shi
19 papers · 2019–2026 · 7 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
๐บ๏ธ Taxonomy Completionist (41) ๐ Academic Marathon ยท Sprint ๐ Conference Polyglot ยท Silver ๐ Interdisciplinary Bridge ยท Silver ๐ฃ Hot Topic Early Bird
๐ค
Dynamic Duo
(12)
๐
Conference Pioneer
๐ฅ
Unstoppable ยท Bronze
๐
Century Club ยท Bronze
๐
Renaissance Researcher
(5)
๐๏ธ
Keyword Collector
(87)
Top co-authors
Research topics
Deep Learning
(11)
Machine Learning
(10)
Computer Vision
(8)
Artificial Intelligence
(6)
Architectures
(6)
Processing
(6)
Core AI
(5)
Core Methods
(5)
Learning Types ยท Machine Learning
(5)
Learning Types ยท Deep Learning
(3)
Models
(3)
Natural Language Processing
(2)
Reinforcement Learning
(2)
Generation
(2)
Learning Paradigms
(2)
Keywords
zero-shot learning
(4)
graph neural network
(3)
image classification
(1)
reinforcement learning
(1)
continual learning
(1)
catastrophic forgetting
(1)
semantic segmentation
(1)
domain generalization
(1)
image segmentation
(1)
link prediction
(1)
sample efficiency
(1)
vision transformer
(1)
multi-task learning
(1)
few-shot learning
(1)
non-convex optimization
(1)
contrastive learning
(1)
transfer learning
(1)
image restoration
(1)
open-vocabulary detection
(1)
langevin dynamics
(1)
Papers
Vision Transformers Need More Than Registers
CVPR 2026
WeaveTime: Streaming from Earlier Frames into Emergent Memory in VideoLLMs
CVPR 2026
Joint Graph Rewiring and Feature Denoising via Spectral Resonance
ICLR 2025
Rethinking Query-based Transformer for Continual Image Segmentation
CVPR 2025
Sim-DETR: Unlock DETR for Temporal Sentence Grounding
ICCV 2025
A Graph Dynamics Prior for Relational Inference
AAAI 2024
Part2Object: Hierarchical Unsupervised 3D Instance Segmentation
ECCV 2024
Plain-Det: A Plain Multi-Dataset Object Detector
ECCV 2024
The Devil is in the Object Boundary: Towards Annotation-free Instance Segmentation using Foundation Models
ICLR 2024
Contrastive Grouping With Transformer for Referring Image Segmentation
CVPR 2023
EdaDet: Open-Vocabulary Object Detection Using Early Dense Alignment
ICCV 2023
Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator
NeurIPS 2023
LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for Vision-Language Models
ICCV 2023
Neural Link Prediction with Walk Pooling
ICLR 2022
Spatial and Visual Perspective-Taking via View Rotation and Relation Reasoning for Embodied Reference Understanding
ECCV 2022
Feature Augmented Memory with Global Attention Network for VideoQA
IJCAI 2020
Robust Reinforcement Learning via Adversarial training with Langevin Dynamics
NeurIPS 2020
Towards Ghost-Free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN
AAAI 2020
Self-Supervised Mixture-of-Experts by Uncertainty Estimation
AAAI 2019