Related papers: Entropy-Aware Structural Alignment for Zero-Shot H…

Attention-based methods and Connectionist Temporal Classification (CTC) network have been promising research directions for end-to-end (E2E) Automatic Speech Recognition (ASR). The joint CTC/Attention model has achieved great success by…

Task-aware robotic grasping is a challenging problem that requires the integration of semantic understanding and geometric reasoning. This paper proposes a novel framework that leverages Large Language Models (LLMs) and Quality Diversity…

Image clustering aims to group images in an unsupervised fashion. Traditional methods focus on knowledge from visual space, making it difficult to distinguish between visually similar but semantically different classes. Recent advances in…

Adapting CLIP for anomaly detection on unseen objects has shown strong potential in a zero-shot manner. However, existing methods typically rely on a single textual space to align with visual semantics across diverse objects and domains.…

Hierarchical Text Classification (HTC) involves assigning documents to labels organized within a taxonomy. Most previous research on HTC has focused on supervised methods. However, in real-world scenarios, employing supervised HTC can be…

Graph Retrieval-Augmented Generation (GraphRAG) has emerged as a promising paradigm that organizes external knowledge into structured graphs of entities and relations, enabling large language models (LLMs) to perform complex reasoning…

Image classification, which classifies images by pre-defined categories, has been the dominant approach to visual representation learning over the last decade. Visual learning through image-text alignment, however, has emerged to show…

Named entity recognition (NER) in Chinese is essential but difficult because of the lack of natural delimiters. Therefore, Chinese Word Segmentation (CWS) is usually considered as the first step for Chinese NER. However, models based on…

Zero-shot sketch-based image retrieval (ZS-SBIR) is challenging due to the cross-domain nature of sketches and photos, as well as the semantic gap between seen and unseen image distributions. Previous methods fine-tune pre-trained models…

Arabic Handwritten Character Recognition (AHCR) has recently advanced significantly with deep Convolutional Neural Networks (ConvNets). However, many models in the literature are deep and computationally expensive in terms of parameters and…

Vision-language pretraining on large datasets of images-text pairs is one of the main building blocks of current Vision-Language Models. While with additional training, these models excel in various downstream tasks, including visual…

Relation classification (RC) task is one of fundamental tasks of information extraction, aiming to detect the relation information between entity pairs in unstructured natural language text and generate structured data in the form of…

Zero-shot human skeleton-based action recognition aims to construct a model that can recognize actions outside the categories seen during training. Previous research has focused on aligning sequences' visual and semantic spatial…

Phonetic Cloaking Replacement (PCR), defined as the deliberate use of homophonic or near-homophonic variants to hide toxic intent, has become a major obstacle to Chinese content moderation. While this problem is well-recognized, existing…

Medical image retrieval (MIR) is a critical component of computer-aided diagnosis, yet existing systems suffer from three persistent limitations: uniform feature encoding that fails to account for the varying clinical importance of…

Learning effective representations for Chinese characters presents unique challenges, primarily due to the vast number of characters and their continuous growth, which requires models to handle an expanding category space. Additionally, the…

Object categories are typically organized into a multi-granularity taxonomic hierarchy. When classifying categories at different hierarchy levels, traditional uni-modal approaches focus primarily on image features, revealing limitations in…

Recently, word enhancement has become very popular for Chinese Named Entity Recognition (NER), reducing segmentation errors and increasing the semantic and boundary information of Chinese words. However, these methods tend to ignore the…

We present a system for object recognition based on a semantic graph representation, which the system can learn from image examples. This graph is based on intrinsic properties of objects such as structure and geometry, so it is more robust…

Faithful text image super-resolution (SR) is challenging because each character has a unique structure and usually exhibits diverse font styles and layouts. While existing methods primarily focus on English text, less attention has been…