Quantile treatment effects (QTEs) can characterize the potentially
heter...
Multiview Self-Supervised Learning (MSSL) is based on learning invarianc...
This paper focuses on long-tailed object detection in the semi-supervise...
Recent Self-Supervised Learning (SSL) methods are able to learn feature
...
Prompt tuning, a parameter- and data-efficient transfer learning paradig...
Compiled software is delivered as executable binary code. Developers wri...
Transformers have gained increasing popularity in a wide range of
applic...
Self-attention mechanisms model long-range context by using pairwise
att...
Utilizing text-only data with an external language model (LM) in end-to-...
Open-vocabulary object detection, which is concerned with the problem of...
Accurate channel modeling is the foundation of communication system desi...
We introduce Attention Free Transformer (AFT), an efficient variant of
T...
This paper studies the estimation of network connectedness with focally
...
We study the problem of directly optimizing arbitrary non-differentiable...
With the rapid development of railways, especially high-speed railways, ...
Recent methods for long-tailed instance segmentation still struggle on r...
In most machine learning training paradigms a fixed, often handcrafted, ...
In this work the modeling and calibration method of reciprocity error in...
We present a novel approach for the task of human pose transfer, which a...
Due to the emergence of Generative Adversarial Networks, video synthesis...
We consider the estimation and inference in a system of high-dimensional...
Data for face analysis often exhibit highly-skewed class distribution, i...
The task of face attribute manipulation has found increasing application...
We investigate the scenario that a robot needs to reach a designated goa...
Stochastic Gradient Descent (SGD) is the central workhorse for training
...
Visual object tracking is a fundamental and time-critical vision task. R...
The ability to ask questions is a powerful tool to gather information in...
In this paper, we propose the first higher frame rate video dataset (cal...
Existing deep embedding methods in vision tasks are capable of learning ...
Data imbalance is common in many vision tasks where one or more classes ...