Skip to content

Author

Tien-Dung Mai

We have 5 of 11 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Oct 2026

StimFlow: Synthesizing Brain Activity from Images via Stimulus-conditioned Flow Matching

The inherent variability of fMRI responses across trials encourages a generative view of the stimulus-to-response mapping. Prior generative encoders often operate in compressed latent spaces and condition predominantly on semantic features, which provide limited low-level cues for early visual cortex. We propose StimFl...

Hung Van Bui, D. Vu, Hoang-Son Vo et al. · 0 citations
Conference Aug 2026

Prior-Guided Amodal Mask Completion: Revisiting Late-Stage Spatial Attention in Shape Reconstruction

This paper investigates amodal mask completion under a prior-guided setting, isolating shape reconstruction from upstream detection errors using oracle visible masks and semantic labels. We propose a lightweight 5-channel Swin-UNet that fuses RGB, visible, and edge priors, optimized via a novel Occlusion-Aware Loss to...

V. Nguyen, N. Phan, Tien-Dung Mai · 0 citations
Conference Aug 2026

On the Instability of Saliency Maps under Sparse Perturbations

Understanding the reliability of model explanations remains a critical challenge in deep learning. Prior work has shown that saliency maps can be manipulated by optimizing the input using gradient-based methods, where gradients of the loss with respect to the input are computed to generate dense perturbations that alte...

Khoa Tran, Thai Huy Nguyen, Quan Minh Phan et al. · 0 citations
Conference Aug 2026

SAM-Anchored DINOv3 Soft Calibration for Weakly Supervised Semantic Segmentation

Weakly supervised semantic segmentation (WSSS) aims to train dense prediction models from inexpensive supervision such as image-level labels. Recent foundation models provide complementary capabilities: promptable segmentation models can produce high-coverage object masks, while self-supervised vision transformers prov...

Duc-Hien Nguyen, L. Nguyễn, X. Nguyễn et al. · 0 citations
Conference Aug 2026

SCAmodal: Reasoning Aware Amodal Completion via Semantic Geometric Dual Guidance

Amodal appearance completion in open-world scenarios requires reconstructing the hidden regions of occluded objects, a task that demands both geometric extrapolation and high-level semantic understanding. Conventional methods predominantly rely on geometric priors, often failing to maintain semantic coherence and struc...

Duy Do-Phuong, Nhan Nguyen Viet Thien, Tien-Dung Mai · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.