Out-of-Distribution (OOD) detection is critical for the reliable operati...
Recent Multimodal Large Language Models (MLLMs) are remarkable in
vision...
This paper focuses on long-tailed object detection in the semi-supervise...
Large-scale models trained on broad data have recently become the mainst...
Machine learning models are intrinsically vulnerable to domain shift bet...
Out-of-distribution (OOD) detection is vital to safety-critical machine
...
Prompt tuning, a parameter- and data-efficient transfer learning paradig...
We present a systematic study of domain generalization (DG) for tiny neu...
Existing research addresses scene graph generation (SGG) – a critical
te...
We address the problem of people detection in RGB-D data where we levera...
The size of vision models has grown exponentially over the last few year...
Existing out-of-distribution (OOD) detection literature clearly defines
...
Open-vocabulary object detection, which is concerned with the problem of...
With the rise of powerful pre-trained vision-language models like CLIP, ...
Most existing studies on unsupervised domain adaptation (UDA) assume tha...
Most existing multi-source domain adaptation (MSDA) methods minimize the...
Out-of-distribution (OOD) detection is critical to ensuring the reliabil...
Vision-language pre-training has recently emerged as a promising alterna...
Confidence calibration is of great importance to the reliability of deci...
Convolutional neural networks (CNNs) often have poor generalization
perf...
Most existing research on domain generalization assumes source data gath...
Though convolutional neural networks (CNNs) have demonstrated remarkable...
Generalization to out-of-distribution (OOD) data is a capability natural...
This paper focuses on domain generalization (DG), the task of learning f...
The problem of generalizing deep neural networks from multiple source do...
Machine learning models typically suffer from the domain shift problem w...
Person re-identification (re-ID), which aims to re-identify people acros...
An effective person re-identification (re-ID) model should learn feature...
As an instance-level recognition problem, person re-identification (ReID...
Most existing video summarisation methods are based on either supervised...
Video summarization aims to facilitate large-scale video browsing by
pro...