Related papers: CK-Transformer: Commonsense Knowledge Enhanced Tra…

This research explores the integration of language models and unsupervised anomaly detection in medical imaging, addressing two key questions: (1) Can language models enhance the interpretability of anomaly detection maps? and (2) Can…

A representation is supposed universal if it encodes any element of the visual world (e.g., objects, scenes) in any configuration (e.g., scale, context). While not expecting pure universal representations, the goal in the literature is to…

Emotion recognition in conversation (ERC) aims to detect the emotion for each utterance in a given conversation. The newly proposed ERC models have leveraged pre-trained language models (PLMs) with the paradigm of pre-training and…

Knowledge graph (KG) embedding is a fundamental task in natural language processing, and various methods have been proposed to explore semantic patterns in distinctive ways. In this paper, we propose to learn an ensemble by leveraging…

Convolution neural networks (CNNs) have succeeded in compressive image sensing. However, due to the inductive bias of locality and weight sharing, the convolution operations demonstrate the intrinsic limitations in modeling the long-range…

Referring camouflaged object detection (Ref-COD) aims to identify hidden objects by incorporating reference information such as images and text descriptions. Previous research has transformed reference images with salient objects into…

Answering complex questions about images is an ambitious goal for machine intelligence, which requires a joint understanding of images, text, and commonsense knowledge, as well as a strong reasoning ability. Recently, multimodal…

Conventional Machine Reading Comprehension (MRC) has been well-addressed by pattern matching, but the ability of commonsense reasoning remains a gap between humans and machines. Previous methods tackle this problem by enriching word…

Transformer models pre-trained with a masked-language-modeling objective (e.g., BERT) encode commonsense knowledge as evidenced by behavioral probes; however, the extent to which this knowledge is acquired by systematic inference over the…

In this work, we reimagine classical probing to evaluate knowledge transfer from simple source to more complex target tasks. Instead of probing frozen representations from a complex source task on diverse simple target probing tasks (as…

Document-level relation extraction (RE) aims to identify the relations between entities throughout an entire document. It needs complex reasoning skills to synthesize various knowledge such as coreferences and commonsense. Large-scale…

Recently proposed fine-grained 3D visual grounding is an essential and challenging task, whose goal is to identify the 3D object referred by a natural language sentence from other distractive objects of the same category. Existing works…

Reference resolution, which aims to identify entities being referred to by a speaker, is more complex in real world settings: new referents may be created by processes the agents engage in and/or be salient only because they belong to the…

Knowledge transfer has strong potential to improve hyperspectral image (HSI) classification, yet two inherent challenges fundamentally restrict effective cross-domain transfer: spectral variations caused by different sensors and semantic…

Event coreference resolution (ECR) is the task of determining whether distinct mentions of events within a multi-document corpus are actually linked to the same underlying occurrence. Images of the events can help facilitate resolution when…

Contextual embeddings represent a new generation of semantic representations learned from Neural Language Modelling (NLM) that addresses the issue of meaning conflation hampering traditional word embeddings. In this work, we show that…

Following the major success of neural language models (LMs) such as BERT or GPT-2 on a variety of language understanding tasks, recent work focused on injecting (structured) knowledge from external resources into these models. While on the…

We present a novel unsupervised feature representation learning method, Visual Commonsense Region-based Convolutional Neural Network (VC R-CNN), to serve as an improved visual region encoder for high-level tasks such as captioning and VQA.…

As the use of interactive machines grow, the task of Emotion Recognition in Conversation (ERC) became more important. If the machine-generated sentences reflect emotion, more human-like sympathetic conversations are possible. Since emotion…

Commonsense knowledge acquisition is a key problem for artificial intelligence. Conventional methods of acquiring commonsense knowledge generally require laborious and costly human annotations, which are not feasible on a large scale. In…