13 citations · 14 across the 7 of their papers we have counts for
5 papers · 1 filter
Long-Term Prediction of Natural Video Sequences with Robust Video Predictors
Luke Ditria, Tom Drummond
Predicting high dimensional video sequences is a curiously difficult problem. The number of possible futures for a given video sequence grows exponentially over time due to uncerta…
Knowledge Combination to Learn Rotated Detection Without Rotated Annotation
Tianyu Zhu, Bryce Ferenczi, Pulak Purkait +3
Rotated bounding boxes drastically reduce output ambiguity of elongated objects, making it superior to axis-aligned bounding boxes. Despite the effectiveness, rotated detectors are…
Deep Laparoscopic Stereo Matching with Transformers
Xuelian Cheng, Yiran Zhong, Mehrtash Harandi +3
The self-attention mechanism, successfully employed with the transformer structure is shown promise in many computer vision tasks including image recognition, and object detection.…
Adaptive Poincaré Point to Set Distance for Few-Shot Classification
Rongkai Ma, Pengfei Fang, Tom Drummond +1
Learning and generalizing from limited examples, i,e, few-shot learning, is of core importance to many real-world vision applications. A principal way of achieving few-shot learnin…
Improved RANSAC performance using simple, iterative minimal-set solvers
Edward Rosten, Gerhard Reitmayr, Tom Drummond
RANSAC is a popular technique for estimating model parameters in the presence of outliers. The best speed is achieved when the minimum possible number of points is used to estimate…