Zhiyuan Cheng
5 papers · 2022–2024 · 4 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 ↓
🌍
Conference Polyglot · Bronze
Top co-authors
Research topics
Keywords
monocular depth estimation
(2)
self-supervised learning
(1)
adversarial training
(1)
optical flow estimation
(1)
higher-order relations
(1)
3d object detection
(1)
adversarial attack
(1)
autonomous vehicle
(1)
adversarial patch attack
(1)
camera-lidar fusion
(1)
view synthesis
(1)
black-box scenario
(1)
multi-sensor fusion
(1)
neural network
(1)
multi-scale context
(1)
physical-world attack
(1)
spatial-temporal action localization
(1)
interactive relation network
(1)
pixel-wise regression
(1)
adversarial robustness
(1)
Papers
BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks
ICML 2024
Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection
ICLR 2024
Actor-Multi-Scale Context Bidirectional Higher Order Interactive Relation Network for Spatial-Temporal Action Localization
IJCAI 2023
Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attacks
ICLR 2023
Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches
ECCV 2022