works on

From the 2 of 7 linked papers with an AI index.

activity
20242026
collaborators

6 papers

cs.CV2026

Fine-Grained Food Image Understanding via Target-Aware Data Alignment

Jui-Feng Chi, Wei-Lun Chu, Bruce Coburn +2

The paper introduces a data-centric approach that selects and refines web-collected image‑caption pairs to better train CLIP‑style vision‑language models for fine‑grained food reco…

cs.CV2026

Open-KNEAD: Knowledge-grounded Nutrition Estimation via Agentic Decomposition

Bruce Coburn, Jingbo Yue, Jinge Ma +3

The paper presents Open-KNEAD, a training-free, locally run agentic system that breaks down meal images into individual food items, grounds each to a nutrition database, and improv…

cs.LG2026

Temporal Imbalance of Positive and Negative Supervision in Class-Incremental Learning

Jinge Ma, Fengqing Zhu

With the widespread adoption of deep learning in visual tasks, Class-Incremental Learning (CIL) has become an important paradigm for handling dynamically evolving data distribution…

cs.CV2026

MFP3D: Monocular Food Portion Estimation Leveraging 3D Point Clouds

Jinge Ma, Xiaoyan Zhang, Gautham Vinod +3

Food portion estimation is crucial for monitoring health and tracking dietary intake. Image-based dietary assessment, which involves analyzing eating occasion images using computer…

cs.CV2026

Implicit-Scale 3D Reconstruction for Multi-Food Volume Estimation from Monocular Images

Yuhao Chen, Gautham Vinod, Siddeshwar Raghavan +5

We present Implicit-Scale 3D Reconstruction from Monocular Multi-Food Images, a benchmark dataset designed to advance geometry-based food portion estimation in realistic dining sce…

cs.CV2025

Robust3D-CIL: Robust Class-Incremental Learning for 3D Perception

Jinge Ma, Jiangpeng He, Fengqing Zhu

3D perception plays a crucial role in real-world applications such as autonomous driving, robotics, and AR/VR. In practical scenarios, 3D perception models must continuously adapt…