no code implementations • 24 Jul 2021 • Olga Moskvyak, Frederic Maire, Feras Dayoub, Mahsa Baktashmotlagh
To reduce the need for labeled data, we focus on a semi-supervised approach that requires only a subset of the training data to be labeled.
no code implementations • ICLR 2021 • Olga Moskvyak, Frederic Maire, Feras Dayoub, Mahsa Baktashmotlagh
Keypoint representations are learnt with a semantic keypoint consistency constraint that forces the keypoint detection network to learn similar features for the same keypoint across the dataset.
no code implementations • 26 Aug 2020 • Olga Moskvyak, Frederic Maire, Feras Dayoub, Mahsa Baktashmotlagh
Learning embeddings that are invariant to the pose of the object is crucial in visual image retrieval and re-identification.
no code implementations • 9 Jan 2020 • Olga Moskvyak, Frederic Maire, Feras Dayoub, Mahsa Baktashmotlagh
Our method outperforms the same model without body landmarks input by 26% and 18% on the synthetic and the real datasets respectively.
1 code implementation • 28 Feb 2019 • Olga Moskvyak, Frederic Maire, Asia O. Armstrong, Feras Dayoub, Mahsa Baktashmotlagh
We present a novel system for visual re-identification based on unique natural markings that is robust to occlusions, viewpoint and illumination changes.