Related papers: OpenStance: Real-world Zero-shot Stance Detection

This paper investigates the problem of zero-shot action recognition, in the setting where no training videos with seen actions are available. For this challenging scenario, the current leading approach is to transfer knowledge from the…

In many documents, such as semi-structured webpages, textual semantics are augmented with additional information conveyed using visual elements including layout, font size, and color. Prior work on information extraction from…

Advances in deep learning have enabled the development of models that have exhibited a remarkable tendency to recognize and even localize actions in videos. However, they tend to experience errors when faced with scenes or examples beyond…

Expanding pre-trained zero-shot counting models to handle unseen categories requires more than simply adding new prompts, as this approach does not achieve the necessary alignment between text and visual features for accurate counting. We…

Zero-shot cross-domain dialogue state tracking (DST) enables us to handle task-oriented dialogue in unseen domains without the expense of collecting in-domain data. In this paper, we propose a slot description enhanced generative approach…

Few-shot object detection, learning to adapt to the novel classes with a few labeled data, is an imperative and long-lasting problem due to the inherent long-tail distribution of real-world data and the urgent demands to cut costs of data…

Recent studies have shown remarkable success in unsupervised image-to-image translation. However, if there has no access to enough images in target classes, learning a mapping from source classes to the target classes always suffers from…

There has been significant interest in zero and few-shot learning for dialogue state tracking (DST) due to the high cost of collecting and annotating task-oriented dialogues. Recent work has demonstrated that in-context learning requires…

The problem of entity-typing has been studied predominantly in supervised learning fashion, mostly with task-specific annotations (for coarse types) and sometimes with distant supervision (for fine types). While such approaches have strong…

Structured information extraction from document images usually consists of three steps: text detection, text recognition, and text field labeling. While text detection and text recognition have been heavily studied and improved a lot in…

Audio-based music classification and tagging is typically based on categorical supervised learning with a fixed set of labels. This intrinsically cannot handle unseen labels such as newly added music genres or semantic words that users…

Open-set learning and discovery (OSLD) is a challenging machine learning task in which samples from new (unknown) classes can appear at test time. It can be seen as a generalization of zero-shot learning, where the new classes are not known…

Deep learning has significantly improved the precision of instance segmentation with abundant labeled data. However, in many areas like medical and manufacturing, collecting sufficient data is extremely hard and labeling this data requires…

Previous work on novel object detection considers zero or few-shot settings where none or few examples of each category are available for training. In real world scenarios, it is less practical to expect that 'all' the novel classes are…

We present streaming self-training (SST) that aims to democratize the process of learning visual recognition models such that a non-expert user can define a new task depending on their needs via a few labeled examples and minimal domain…

We propose a method to infer domain-specific models such as classifiers for unseen domains, from which no data are given in the training phase, without domain semantic descriptors. When training and test distributions are different,…

Pretrained language models have shown success in various areas of natural language processing, including reading comprehension tasks. However, when applying machine learning methods to new domains, labeled data may not always be available.…

Stance detection refers to the task of extracting the standpoint (Favor, Against or Neither) towards a target in given texts. Such research gains increasing attention with the proliferation of social media contents. The conventional…

Stance detection automatically detects the stance in a text towards a target, vital for content analysis in web and social media research. Despite their promising capabilities, LLMs encounter challenges when directly applied to stance…

With the development of generative artificial intelligence, new forgery methods are rapidly emerging. Social platforms are flooded with vast amounts of unlabeled synthetic data and authentic data, making it increasingly challenging to…