Search Results for author:
Found 39 papers, 17 papers with code
A Survey of Guidelines and Best Practices for the Generation, Interlinking, Publication, and Validation of Linguistic Linked Data
This article discusses a survey carried out within the NexusLinguarum COST Action which aimed to give an overview of existing guidelines (GLs) and best practices (BPs) in linguistic linked data.
From Inscriptions to Lexica and Back: A Platform for Editing and Linking the Languages of Ancient Italy
Available language technology is hardly applicable to scarcely attested ancient languages, yet their digital semantic representation, though challenging, is an asset for the purpose of sharing and preserving existing cultural knowledge.
Computational Morphology with OntoLex-Morph
This paper describes the current status of the emerging OntoLex module for linguistic morphology.
Towards the Construction of a WordNet for Old English
In this paper we will discuss our preliminary work towards the construction of a WordNet for Old English, taking our inspiration from other similar WN construction projects for ancient languages such as Ancient Greek, Latin and Sanskrit.
Modelling Collocations in OntoLex-FrAC
Following presentations of frequency and attestations, and embeddings and distributional similarity, this paper introduces the third cornerstone of the emerging OntoLex module for Frequency, Attestation and Corpus-based Information, OntoLex-FrAC.
How Good is my Histopathology Vision-Language Foundation Model? A Holistic Benchmark
We systematically evaluate existing histopathology VLMs on Histo-VL to simulate diverse tasks performed by experts in real-world clinical scenarios.
KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding
We present KITAB-Bench, a comprehensive Arabic OCR benchmark that fills the gaps in current evaluation systems.
Robust-LLaVA: On the Effectiveness of Large-Scale Robust Image Encoders for Multi-modal Large Language Models
Multi-modal Large Language Models (MLLMs) excel in vision-language tasks but remain vulnerable to visual adversarial perturbations that can induce hallucinations, manipulate responses, or bypass safety mechanisms.
BiMediX2: Bio-Medical EXpert LMM for Diverse Medical Modalities
This paper introduces BiMediX2, a bilingual (Arabic-English) Bio-Medical EXpert Large Multimodal Model (LMM) with a unified architecture that integrates text and visual modalities, enabling advanced image understanding and medical applications.
All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages
In pursuit of culturally diverse global multimodal models, our proposed All Languages Matter Benchmark (ALM-bench) represents the largest and most comprehensive effort to date for evaluating LMMs across 100 languages.
AgriCLIP: Adapting CLIP for Agriculture and Livestock via Domain-Specialized Cross-Model Alignment
Further, this domain desires fine-grained feature learning due to the subtle nature of the downstream tasks (e. g, nutrient deficiency detection, livestock breed classification).
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding
Building on the advances of language models, Large Multimodal Models (LMMs) have contributed significant improvements in video understanding.
Ranked #1 on
VCGBench-Diverse
on VideoInstruct
MedContext: Learning Contextual Cues for Efficient Volumetric Medical Segmentation
The proposed approach induces contextual knowledge in the network by learning to reconstruct the missing organ or parts of an organ in the output segmentation space.
Distilling Local Texture Features for Colorectal Tissue Classification in Low Data Regimes
Multi-class colorectal tissue classification is a challenging problem that is typically addressed in a setting, where it is assumed that ample amounts of training data is available.
VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learning
Salient object detection (SOD) and camouflaged object detection (COD) are related yet distinct binary mapping tasks.
PG-Video-LLaVA: Pixel Grounding Large Video-Language Models
Extending image-based Large Multimodal Models (LMMs) to videos is challenging due to the inherent complexity of video data.
Sentence-level Prompts Benefit Composed Image Retrieval
Composed image retrieval (CIR) is the task of retrieving specific images by using a query that involves both a reference image and a relative caption.
Ranked #3 on
Image Retrieval
on CIRR
3D Indoor Instance Segmentation in an Open-World
We argue that such a closed-world assumption is restrictive and explore for the first time 3D indoor instance segmentation in an open-world setting, where the model is allowed to distinguish a set of known classes as well as identify an unknown object as unknown and then later incrementally learning the semantic category of the unknown when the corresponding category labels are available.
Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment
To address this challenge, we propose the Self Structural Semantic Alignment (S^3A) framework, which extracts the structural semantic information from unlabeled data while simultaneously self-learning.
LEAPS: End-to-End One-Step Person Search With Learnable Proposals
Given a set of sparse and learnable proposals, LEAPS employs a dynamic person search head to directly perform person detection and corresponding re-id feature generation without non-maximum suppression post-processing.
Boosting Adversarial Transferability using Dynamic Cues
Our temporal prompts are the result of a learnable transformation that allows optimizing for temporal gradients during an adversarial attack to fool the motion dynamics.
PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery
The GNCD setting aims to categorize unlabeled training data coming from known and novel classes by leveraging the information of partially labeled known classes.
CLIP model is an Efficient Continual Learner
In this work, we show that a frozen CLIP (Contrastive Language-Image Pretraining) model offers astounding continual learning performance without any fine-tuning (zero-shot evaluation).
D3Former: Debiased Dual Distilled Transformer for Incremental Learning
In contrast to a recent ViT based CIL approach, our $\textrm{D}^3\textrm{Former}$ does not dynamically expand its architecture when new tasks are learned and remains suitable for a large number of incremental tasks.
On the Robustness of 3D Object Detectors
To the best of our knowledge, we are the first to investigate the robustness of point-based 3D object detectors.
Modelling Etymology in LMF/TEI: The Grande Dicion\'ario Houaiss da L\'\ingua Portuguesa Dictionary as a Use Case
In this article we will introduce two of the new parts of the new multi-part version of the Lexical Markup Framework (LMF) ISO standard, namely part 3 of the standard (ISO 24613-3), which deals with etymological and diachronic data, and Part 4 (ISO 24613-4), which consists of a TEI serialisation of all of the prior parts of the model.
Representing Temporal Information in Lexical Linked Data Resources
The increasing recognition of the utility of Linked Data as a means of publishing lexical resource has helped to underline the need for RDF based data models which have the flexibility and expressivity to be able to represent the most salient kinds of information contained in such resources as structured data, including, notably, information relating to time and the temporal dimension.
A Multilingual Evaluation Dataset for Monolingual Word Sense Alignment
Aligning senses across resources and languages is a challenging task with beneficial applications in the field of natural language processing and electronic lexicography.
LMF Reloaded
Lexical Markup Framework (LMF) or ISO 24613 [1] is a de jure standard that provides a framework for modelling and encoding lexical information in retrodigitised print dictionaries and NLP lexical databases.
Tools and Instruments for Building and Querying Diachronic Computational Lexica
This article describes work on enabling the addition of temporal information to senses of words in linguistic linked open data lexica based on the lemonDia model.
LREC as a Graph: People and Resources in a Network
This proposal describes a new way to visualise resources in the LREMap, a community-built repository of language resource descriptions and uses.
Al Qamus al Muhit, a Medieval Arabic Lexicon in LMF
This paper describes the conversion into LMF, a standard lexicographic digital format of {`}al-q{\=a}m{\=u}s al-muḥ{\=\i}ṭ, a Medieval Arabic lexicon.
The IMAGACT Visual Ontology. An Extendable Multilingual Infrastructure for the representation of lexical encoding of Action
IMAGACT makes explicit the variation of meaning of action verbs within one language and allows comparisons of verb variations within and across languages.
