Unmasked Teacher: Towards Training-Efficient Video Foundation Models
March 28, 2023
| | | | | |
Computer Science
Computer Vision and Pattern Recognition
Video Foundation Models (VFMs) have received limited exploration due to high
computational costs and data scarcity. Previous VFMs rely on Image Foundation
Models (IFMs), which face challenges in transferring to the video domain.
Although Vi...
Cohomological rank functions and syzygies of projective bundles on
abelian varieties
March 28, 2023
|
Mathematics
Algebraic Geometry
We use Jiang--Pareschi's cohomological rank functions and techniques
developed by Caucci and Ito to study syzygies of projective bundles on abelian
varieties. Consequently, we generalize and refine Chiantipalli's results
regarding property ...
Control Barrier Functions in Dynamic UAVs for Kinematic Obstacle
Avoidance: A Collision Cone Approach
March 28, 2023
| | |
Computer Science
Robotics
Unmanned aerial vehicles (UAVs), specifically quadrotors, have revolutionized
various industries with their maneuverability and versatility, but their safe
operation in dynamic environments heavily relies on effective collision
avoidance te...
Carbon-Chain Chemistry in the Interstellar Medium
March 28, 2023
| |
Physics
Astrophysics of Galaxies
Solar and Stellar Astrophysics
The presence of carbon-chain molecules in the interstellar medium (ISM) has
been known since the early 1970s and >130 such species have been identified
to date, making up ∼43% of the total of detected ISM molecules. They are
prevale...
Dehn filling and the knot group I: Realization Property
March 28, 2023
| |
Mathematics
Geometric Topology
Group Theory
Each r--Dehn filling of the exterior E(K) of a knot K in S3 produces
a 3--manifold K(r), and induces an epimorphism from the knot group G(K)=π1(E(K)) to π1(K(r)), which trivializes elements in its kernel. To
each el...
Adaptive Background Music for a Fighting Game: A Multi-Instrument Volume
Modulation Approach
March 28, 2023
| | |
Electrical Engineering and Systems Science
Computer Science
Audio and Speech Processing
Artificial Intelligence
Sound
This paper presents our work to enhance the background music (BGM) in
DareFightingICE by adding an adaptive BGM. The adaptive BGM consists of five
different instruments playing a classical music piece called "Air on G-String."
The BGM adapt...
When does subtracting a rank-one approximation decrease tensor rank?
March 27, 2023
| | |
Mathematics
Algebraic Geometry
Metric Geometry
Optimization and Control
Algebraic Geometry
Metric Geometry
Optimization and Control
Subtracting a critical rank-one approximation from a matrix always results in
a matrix with a lower rank. This is not true for tensors in general. Motivated
by this, we ask the question: what is the closure of the set of those tensors
for w...
Gillespie algorithm for quantum jump trajectories
March 27, 2023
| | | | |
Physics
Quantum Physics
Statistical Mechanics
Quantum Physics
Statistical Mechanics
The jump unravelling of a quantum master equation decomposes the dynamics of
an open quantum system into abrupt jumps, interspersed by periods of coherent
dynamics when no jumps occur. Such open quantum systems are ubiquitous in
quantum opt...
A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
March 27, 2023
| | | | |
Computer Science
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine learning methods strive to acquire a robust model during the training
process that can effectively generalize to test samples, even in the presence
of distribution shifts. However, these methods often suffer from performance
degrada...
StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing
March 27, 2023
| | | | | | | | | | and others
Computer Science
Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
A significant research effort is focused on exploiting the amazing capacities
of pretrained diffusion models for the editing of images.They either finetune
the model, or invert the image in the latent space of the pretrained model.
However,...