Matthew Kowal

7 papers · 2021–2025 · 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 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (14)

Venues

CVPR (3) ICML (2) ICCV (1) ICLR (1)

Top co-authors

Konstantinos G. Derpanis (6) Md Amirul Islam (3) Thomas FEL (2) Neil D. B. Bruce (2) Richard P. Wildes (2) Sen Jia (2) Jacob S. Prince (1) Victor Boutin (1) Binxu Wang (1) Patrick Esser (1)

Research topics

Computer Vision (5) Deep Learning (5) Artificial Intelligence (4) Core AI (4) Machine Learning (3) Analysis (3) Architectures (3) Core Methods (3) Processing (3) Learning Types (1) Optimization & Theory (1) Techniques (1)

Keywords

action recognition (2) video segmentation (2) representation learning (2) concept discovery (2) convolutional neural network (2) video transformer (1) network structure (1) autoencoders (1) identifiability (1) stability (1) latent representation (1) convex hull (1) position encoding (1) discriminative feature (1) concept alignment (1) deep network (1) spatio-temporal network (1) spatiotemporal model (1) shape bia (1) texture bia (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