Zihang Lai
11 papers · 2020–2026 · 3 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
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(24)
💎
Century Club · Bronze
Top co-authors
Research topics
Computer Vision
(9)
Analysis
(8)
Deep Learning
(6)
Artificial Intelligence
(4)
Architectures
(4)
Core AI
(4)
Processing
(4)
Machine Learning
(3)
Learning Types · Machine Learning
(2)
Reinforcement Learning
(1)
Application Areas
(1)
Core Methods
(1)
Learning Paradigms
(1)
Learning Types · Deep Learning
(1)
Methods
(1)
Keywords
3d reconstruction
(2)
point tracking
(2)
dynamic point map
(2)
self-supervised learning
(2)
motion estimation
(1)
video recognition
(1)
semantic segmentation
(1)
object tracking
(1)
video prediction
(1)
efficient computing
(1)
computational efficiency
(1)
motion segmentation
(1)
optical flow
(1)
visual tracking
(1)
visual correspondence
(1)
disentangled representation
(1)
adaptive computation
(1)
vision-language model
(1)
zero-shot generalization
(1)
video understanding
(1)
Papers
CoWTracker: Tracking by Warping instead of Correlation
CVPR 2026
V-DPM: 4D Video Reconstruction with Dynamic Point Maps
CVPR 2026
Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction
ICCV 2025
Exploring Simple Open-Vocabulary Semantic Segmentation
CVPR 2025
Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better
CVPR 2025
ActiveNeRF: Learning Where to See with Uncertainty Estimation
ECCV 2022
AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition
CVPR 2022
Learning to Weight Samples for Dynamic Early-Exiting Networks
ECCV 2022
The Functional Correspondence Problem
ICCV 2021
Video Autoencoder: Self-Supervised Disentanglement of Static 3D Structure and Motion
ICCV 2021
MAST: A Memory-Augmented Self-Supervised Tracker
CVPR 2020