Matthew Kowal
7 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (4) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (13) π§ Keyword Pioneer π Cross-Pollinator (15)
π
Keyword Champion
(2)
Conferences
CVPR (3)
ICML (2)
ICCV (1)
ICLR (1)
Top co-authors
Keywords
representation learning
(2)
action recognition
(2)
video segmentation
(2)
concept discovery
(2)
network structure
(1)
latent representation
(1)
convolutional neural network
(1)
position encoding
(1)
deep network
(1)
spatiotemporal model
(1)
video object segmentation
(1)
neural network
(1)
interpretable concept
(1)
static information
(1)
dynamic information
(1)
global pooling
(1)
channel-wise representation
(1)
fine-grained concept
(1)
spatiotemporal network
(1)
unsupervised learning
(1)
Papers
Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models
ICML 2025
Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment
ICML 2025
Understanding Video Transformers via Universal Concept Discovery
CVPR 2024
Visual Concept Connectome (VCC): Open World Concept Discovery and their Interlayer Connections in Deep Models
CVPR 2024
A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information
CVPR 2022
Global Pooling, More Than Meets the Eye: Position Information Is Encoded Channel-Wise in CNNs
ICCV 2021
Shape or Texture: Understanding Discriminative Features in CNNs
ICLR 2021