output
20082026
most citedAnabranch Network for Camouflaged Object Segmentation

753 citations

123 papers

cs.CV2026★ 10 cited

Vision And Text Transformer For Predicting Answerability On Visual Question Answering

Tung Le, Huy Tien Nguyen, Le Minh Nguyen

Answerability on Visual Question Answering is a novel and attractive task to predict answerable scores between images and questions in multi-modal data. Existing works often utiliz…

math-ph2026★ 1 cited

Local Density Approximation and Other Limit Regimes for a Homogeneous Bose Gas with Repulsive Three-Body Interactions in Low-Dimensional Space

Thi Anh Thu Doan, Dinh-Thi Nguyen

In the whole space of low spatial dimensions, namely , we study the minimizers of an energy functional with an attractive cubic nonlinearity and a repulsive quintic nonli…

math-ph2026

Homogeneous attractive Bose-Einstein condensates with repulsive three-body interactions: the two-dimensional case

Dinh-Thi Nguyen

We consider a homogeneous Bose gas composed of identical bosons occupying an infinite two-dimensional space. This gas exhibits both an attractive two-body interaction and a rep…

nucl-th2026★ 5 cited

On the Bohr-Sommerfeld quantization condition and assault frequency in a semiclassical model for α decay

Le Hoang Chien, Nguyen Tri Toan Phuc

We study the impacts of the Bohr-Sommerfeld quantization condition and the assault frequency on the α decay half-life within the semiclassical model. The potential between the α pa…

cs.MM2026

Contestable Multi-Agent Debate with Arena-based Argumentative Computation for Multimedia Verification

Truong Thanh Hung Nguyen, Vo Thanh Khang Nguyen, Hoang-Loc Cao +3

Multimedia verification requires not only accurate conclusions but also transparent and contestable reasoning. We propose a contestable multi-agent framework that integrates multim…

cs.IR2026

GeoSearch: Augmenting Worldwide Geolocalization with Web-Scale Reverse Image Search and Image Matching

Tung-Duong Le-Duc, Hoang-Quoc Nguyen-Son, Minh-Son Dao

Worldwide image geolocalization, which aims to predict the GPS coordinates of any image on Earth, remains challenging due to global visual diversity. Recent generative approaches b…