joseph heyward
5 papers · 2023–2025 · 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
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(17)
👥
Mega-Team · Squad
Venues
Top co-authors
Research topics
Machine Learning
(4)
Learning Types · Machine Learning
(4)
Computer Vision
(3)
Artificial Intelligence
(2)
Deep Learning
(2)
Core AI · Artificial Intelligence
(2)
Core Methods
(2)
Learning Types · Deep Learning
(2)
Processing
(2)
Analysis
(1)
Core AI · Computer Vision
(1)
Domain-Specific
(1)
Optimization & Theory · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Keywords
self-supervised learning
(3)
representation learning
(3)
video understanding
(2)
video representation
(2)
online learning
(1)
domain generalization
(1)
transfer learning
(1)
domain adaptation
(1)
scene understanding
(1)
video prediction
(1)
multimodal learning
(1)
future prediction
(1)
spatiotemporal model
(1)
video representation learning
(1)
streaming video
(1)
video foundation model
(1)
scientific video
(1)
orthogonal gradient
(1)
continuous video stream
(1)
continual learning
(1)
Papers
Learning from Streaming Video with Orthogonal Gradients
CVPR 2025
SciVid: Cross-Domain Evaluation of Video Models in Scientific Applications
ICCV 2025
Learning from One Continuous Video Stream
CVPR 2024
Moving Off-the-Grid: Scene-Grounded Video Representations
NeurIPS 2024
Perception Test: A Diagnostic Benchmark for Multimodal Video Models
NeurIPS 2023