1 citations · 1 across the 9 of their papers we have counts for
8 papers · 1 filter
How Much Future Helps? A Controlled Study of Future-Privileged Supervision for Causal Egocentric Gaze Estimation
Jia Li, Wenjie Zhao, Fnu Atisri +5
Egocentric gaze estimation is commonly studied using models that process the full video with access to future frames, while real-world applications require strictly causal, online…
CURE-OOD: Benchmarking Out-of-Distribution Detection for Survival Prediction
Wenjie Zhao, Jia Li, Mingrui Liu +2
``How long can I live and remain free of cancer?'' is often the first question a patient asks after receiving a cancer diagnosis and treatment. Accurate survival prediction helps a…
Mitigating the ID-OOD Tradeoff in Open-Set Test-Time Adaptation
Wenjie Zhao, Jia Li, Xin Dong +3
Open-set test-time adaptation (OSTTA) addresses the challenge of adapting models to new environments where out-of-distribution (OOD) samples coexist with in-distribution (ID) sampl…
ARGaze: Autoregressive Transformers for Online Egocentric Gaze Estimation
Jia Li, Wenjie Zhao, Shijian Deng +6
Online egocentric gaze estimation predicts where a camera wearer is looking from first-person video using only past and current frames, a task essential for augmented reality and a…
MetaRank: Task-Aware Metric Selection for Model Transferability Estimation
Yuhang Liu, Wenjie Zhao, Xin Wang +1
Selecting an appropriate pre-trained source model is a critical, yet computationally expensive, task in transfer learning. Model Transferability Estimation (MTE) methods address th…
From Pixel to Mask: A Survey of Out-of-Distribution Segmentation
Wenjie Zhao, Jia Li, Yunhui Guo
Out-of-distribution (OoD) detection and segmentation have attracted growing attention as concerns about AI security rise. Conventional OoD detection methods identify the existence…
H2ST: Hierarchical Two-Sample Tests for Continual Out-of-Distribution Detection
Yuhang Liu, Wenjie Zhao, Yunhui Guo
Task Incremental Learning (TIL) is a specialized form of Continual Learning (CL) in which a model incrementally learns from non-stationary data streams. Existing TIL methodologies…
Segment Every Out-of-Distribution Object
Wenjie Zhao, Jia Li, Xin Dong +2
Semantic segmentation models, while effective for in-distribution categories, face challenges in real-world deployment due to encountering out-of-distribution (OoD) objects. Detect…