5 citations · 5 across the 4 of their papers we have counts for
7 papers
Are We Measuring Anticipation? Auditing Privileged Information in Procedural Video Evaluation
Mahsa Mohammadi, Sareh Rowlands
Benchmark scores license claims about the capabilities being evaluated. We audit the inference licensed by an evaluation protocol, rather than the predictive model alone. Using pro…
Language-Augmented Video Action Anticipation: Design Fundamentals, Benchmarks, and Open Challenges
Mahsa Mohammadi, Zeyu Fu, Sareh Rowlands
Action anticipation predicts future human actions from partial video under incomplete context and temporal uncertainty. Recent systems introduce large language models (LLMs), visio…
Reliable Egocentric Action Anticipation via Temporal Reliability Suppression and Compositional Graph Decoding
Mahsa Mohammadi, Sareh Rowlands
Wearable action anticipation systems must remain reliable despite missing frames, masking, and sensor noise, yet existing egocentric anticipation methods largely assume clean obser…
Bridging Domain Gaps for Fine-Grained Moth Classification Through Expert-Informed Adaptation and Foundation Model Priors
Ross J Gardiner, Guillaume Mougeot, Sareh Rowlands +3
Labelling images of Lepidoptera (moths) from automated camera systems is vital for understanding insect declines. However, accurate species identification is challenging due to dom…
Distributed Black-box Attack: Do Not Overestimate Black-box Attacks
Han Wu, Sareh Rowlands, Johan Wahlstrom
As cloud computing becomes pervasive, deep learning models are deployed on cloud servers and then provided as APIs to end users. However, black-box adversarial attacks can fool ima…
Adversarial Detection: Attacking Object Detection in Real Time
Han Wu, Syed Yunas, Sareh Rowlands +2
Intelligent robots rely on object detection models to perceive the environment. Following advances in deep learning security it has been revealed that object detection models are v…
A Human-in-the-Middle Attack against Object Detection Systems
Han Wu, Sareh Rowlands, Johan Wahlstrom
Object detection systems using deep learning models have become increasingly popular in robotics thanks to the rising power of CPUs and GPUs in embedded systems. However, these mod…