41 citations · 148 across the 32 of their papers we have counts for
34 papers
Region-Aware CLS Token Augmentation for Fine-Grained Image Retrieval
Ian de Holanda Cavalcanti Bezerra, Vivek Trivedy, Lucas Pascotti Valem +1
Image retrieval methods often rely on a single global semantic descriptor extracted from an image, e.g., the [CLS] token in vision transformers. However, trying to squeeze all the…
ERUnderstand: Evaluating Vision-Language Models on Structured ER Diagrams
Ali Ansari, Yasmin Mohammadi, Farnoush Nili +3
Entity-Relationship Diagrams (ERDs) are central to conceptual database design, yet they are typically available only as rendered images rather than machine-readable schemas, limiti…
Scaling Performance and Low-Resource Annotation with Many-Shot In-Context Learning for Named Entity Recognition
Qi Zhang, Fangping Lan, Cornelia Caragea +2
In-context learning (ICL) with large language models (LLMs) has emerged as a powerful alternative to fine-tuning for Named Entity Recognition (NER), achieving strong performance wi…
Enhancing Renal Tumor Malignancy Prediction: Deep Learning with Automatic 3D CT Organ Focused Attention
Zhengkang Fan, Chengkun Sun, Russell Terry +2
Accurate prediction of malignancy in renal tumors is crucial for informing clinical decisions and optimizing treatment strategies. However, existing imaging modalities lack the nec…
Logit Lens Supervision for Patch-Level Explanations in Vision-Language Models
Parsa Esmaeilkhani, Longin Jan Latecki
Modern autoregressive Vision-Language Models (VLMs) can generate fluent answers while their visual-token representations become weakly tied to the image regions from which they ori…
Direct Visual Grounding by Directing Attention of Visual Tokens
Parsa Esmaeilkhani, Longin Jan Latecki
Vision Language Models (VLMs) mix visual tokens and text tokens. A puzzling issue is the fact that visual tokens most related to the query receive little to no attention in the fin…
Layout Stroke Imitation: A Layout Guided Handwriting Stroke Generation for Style Imitation with Diffusion Model
Sidra Hanif, Longin Jan Latecki
Handwriting stroke generation is crucial for improving the performance of tasks such as handwriting recognition and writers order recovery. In handwriting stroke generation, it is…
Querying Climate Knowledge: Semantic Retrieval for Scientific Discovery
Mustapha Adamu, Qi Zhang, Huitong Pan +2
The growing complexity and volume of climate science literature make it increasingly difficult for researchers to find relevant information across models, datasets, regions, and va…
Learning Object Focused Attention
Vivek Trivedy, Amani Almalki, Longin Jan Latecki
We propose an adaptation to the training of Vision Transformers (ViTs) that allows for an explicit modeling of objects during the attention computation. This is achieved by adding…
DynClean: Training Dynamics-based Label Cleaning for Distantly-Supervised Named Entity Recognition
Qi Zhang, Huitong Pan, Zhijia Chen +3
Distantly Supervised Named Entity Recognition (DS-NER) has attracted attention due to its scalability and ability to automatically generate labeled data. However, distant annotatio…
SciER: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documents
Qi Zhang, Zhijia Chen, Huitong Pan +3
Scientific information extraction (SciIE) is critical for converting unstructured knowledge from scholarly articles into structured data (entities and relations). Several datasets…
FlowLearn: Evaluating Large Vision-Language Models on Flowchart Understanding
Huitong Pan, Qi Zhang, Cornelia Caragea +2
Flowcharts are graphical tools for representing complex concepts in concise visual representations. This paper introduces the FlowLearn dataset, a resource tailored to enhance the…
SciDMT: A Large-Scale Corpus for Detecting Scientific Mentions
Huitong Pan, Qi Zhang, Cornelia Caragea +2
We present SciDMT, an enhanced and expanded corpus for scientific mention detection, offering a significant advancement over existing related resources. SciDMT contains annotated s…
VAPO: Visibility-Aware Keypoint Localization for Efficient 6DoF Object Pose Estimation
Ruyi Lian, Yuewei Lin, Longin Jan Latecki +1
Localizing predefined 3D keypoints in a 2D image is an effective way to establish 3D-2D correspondences for instance-level 6DoF object pose estimation. However, unreliable localiza…
Enhanced Masked Image Modeling for Analysis of Dental Panoramic Radiographs
Amani Almalki, Longin Jan Latecki
The computer-assisted radiologic informative report has received increasing research attention to facilitate diagnosis and treatment planning for dental care providers. However, ma…
DMDD: A Large-Scale Dataset for Dataset Mentions Detection
Huitong Pan, Qi Zhang, Eduard Dragut +2
The recognition of dataset names is a critical task for automatic information extraction in scientific literature, enabling researchers to understand and identify research opportun…
Graph Convolutional Networks based on Manifold Learning for Semi-Supervised Image Classification
Lucas Pascotti Valem, Daniel Carlos Guimarães Pedronette, Longin Jan Latecki
Due to a huge volume of information in many domains, the need for classification methods is imperious. In spite of many advances, most of the approaches require a large amount of l…
Rank Flow Embedding for Unsupervised and Semi-Supervised Manifold Learning
Lucas Pascotti Valem, Daniel Carlos Guimarães Pedronette, Longin Jan Latecki
Impressive advances in acquisition and sharing technologies have made the growth of multimedia collections and their applications almost unlimited. However, the opposite is true fo…
Weakly Supervised Annotations for Multi-modal Greeting Cards Dataset
Sidra Hanif, Longin Jan Latecki
In recent years, there is a growing number of pre-trained models trained on a large corpus of data and yielding good performance on various tasks such as classifying multimodal dat…
Self-Supervised Learning with Masked Image Modeling for Teeth Numbering, Detection of Dental Restorations, and Instance Segmentation in Dental Panoramic Radiographs
Amani Almalki, Longin Jan Latecki
The computer-assisted radiologic informative report is currently emerging in dental practice to facilitate dental care and reduce time consumption in manual panoramic radiographic…
DPNet: Dual-Path Network for Real-time Object Detection with Lightweight Attention
Quan Zhou, Huimin Shi, Weikang Xiang +3
The recent advances of compressing high-accuracy convolution neural networks (CNNs) have witnessed remarkable progress for real-time object detection. To accelerate detection speed…
DRBANET: A Lightweight Dual-Resolution Network for Semantic Segmentation with Boundary Auxiliary
Linjie Wang, Quan Zhou, Chenfeng Jiang +2
Due to the powerful ability to encode image details and semantics, many lightweight dual-resolution networks have been proposed in recent years. However, most of them ignore the be…
DPNET: Dual-Path Network for Efficient Object Detectioj with Lightweight Self-Attention
Huimin Shi, Quan Zhou, Yinghao Ni +2
Object detection often costs a considerable amount of computation to get satisfied performance, which is unfriendly to be deployed in edge devices. To address the trade-off between…
Pushing the Envelope of Rotation Averaging for Visual SLAM
Xinyi Li, Lin Yuan, Longin Jan Latecki +1
As an essential part of structure from motion (SfM) and Simultaneous Localization and Mapping (SLAM) systems, motion averaging has been extensively studied in the past years and co…