Search Results for author:
Found 4 papers, 3 papers with code
Manifold Hypothesis in Data Analysis: Double Geometrically-Probabilistic Approach to Manifold Dimension Estimation
The probabilistic method is new.
MDMMT: Multidomain Multimodal Transformer for Video Retrieval
We present a new state-of-the-art on the text to video retrieval task on MSRVTT and LSMDC benchmarks where our model outperforms all previous solutions by a large margin.
Ranked #25 on
Video Retrieval
on LSMDC
(using extra training data)
Mutual Modality Learning for Video Action Classification
In this paper, we explore the various methods to embed the ensemble power into a single model.
Ranked #47 on
Action Recognition
on Something-Something V2
(using extra training data)
AdvHat: Real-world adversarial attack on ArcFace Face ID system
In this paper we propose a novel easily reproducible technique to attack the best public Face ID system ArcFace in different shooting conditions.
