Search Results for author:
Found 6 papers, 4 papers with code
Humans disagree with the IoU for measuring object detector localization error
Our work is the first to evaluate IoU with humans and makes it clear that relying on IoU scores alone to evaluate localization errors might not be sufficient.
Video BagNet: short temporal receptive fields increase robustness in long-term action recognition
Previous work on long-term video action recognition relies on deep 3D-convolutional models that have a large temporal receptive field (RF).
Are current long-term video understanding datasets long-term?
In the current deep learning paradigm for automatic action recognition, it is imperative that models are trained and tested on datasets and tasks that evaluate if such models actually learn and reason over long-term information.
Benchmarking Data Efficiency and Computational Efficiency of Temporal Action Localization Models
This work explores and measures how current deep temporal action localization models perform in settings constrained by the amount of data or computational power.
Can we predict the Most Replayed data of video streaming platforms?
To this end, we curate a large video benchmark, the YTMR500 dataset, which comprises 500 YouTube videos with MR data annotations.
Do Object Detection Localization Errors Affect Human Performance and Trust?
Bounding boxes are often used to communicate automatic object detection results to humans, aiding humans in a multitude of tasks.
