Focusing On Targets For Improving Weakly Supervised Visual Grounding

no code implementations • 22 Feb 2023 • Viet-Quoc Pham, Nao Mishima

Weakly supervised visual grounding aims to predict the region in an image that corresponds to a specific linguistic query, where the mapping between the target object and query is unknown in the training stage.

Dependency Parsing Object +1

BiSeg: Simultaneous Instance Segmentation and Semantic Segmentation with Fully Convolutional Networks

no code implementations • 7 Jun 2017 • Viet-Quoc Pham, Satoshi Ito, Tatsuo Kozakaya

We present a simple and effective framework for simultaneous semantic segmentation and instance segmentation with Fully Convolutional Networks (FCNs).

Bayesian Inference Instance Segmentation +3

COUNT Forest: CO-Voting Uncertain Number of Targets Using Random Forest for Crowd Density Estimation

no code implementations • ICCV 2015 • Viet-Quoc Pham, Tatsuo Kozakaya, Osamu Yamaguchi, Ryuzo Okada

This paper presents a patch-based approach for crowd density estimation in public scenes.

Density Estimation Scene Understanding