activity
20132026
most citedEstimating Skin Tone and Effects on Classification Performance in Dermatology Datasets

37 citations · 124 across the 20 of their papers we have counts for

collaborators
Showing cs.CVShow all

9 papers · 1 filter

cs.CV2021

Detector-Free Weakly Supervised Grounding by Separation

Assaf Arbelle, Sivan Doveh, Amit Alfassy +14

Nowadays, there is an abundance of data involving images and surrounding free-form text weakly corresponding to those images. Weakly Supervised phrase-Grounding (WSG) deals with th…

cs.CV202121 cited

AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition

Yue Meng, Rameswar Panda, Chung-Ching Lin +5

Temporal modelling is the key for efficient video action recognition. While understanding temporal information can improve recognition accuracy for dynamic actions, removing tempor…

cs.CV20204 cited

OnlineAugment: Online Data Augmentation with Less Domain Knowledge

Zhiqiang Tang, Yunhe Gao, Leonid Karlinsky +3

Data augmentation is one of the most important tools in training modern deep neural networks. Recently, great advances have been made in searching for optimal augmentation policies…

cs.CV202010 cited

AR-Net: Adaptive Frame Resolution for Efficient Action Recognition

Yue Meng, Chung-Ching Lin, Rameswar Panda +5

Action recognition is an open and challenging problem in computer vision. While current state-of-the-art models offer excellent recognition results, their computational expense lim…

cs.CV2020

TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classification

Moshe Lichtenstein, Prasanna Sattigeri, Rogerio Feris +2

The field of Few-Shot Learning (FSL), or learning from very few (typically or ) examples per novel class (unseen during training), has received a lot of attention and signif…

cs.CV2020

StarNet: towards Weakly Supervised Few-Shot Object Detection

Leonid Karlinsky, Joseph Shtok, Amit Alfassy +8

Few-shot detection and classification have advanced significantly in recent years. Yet, detection approaches require strong annotation (bounding boxes) both for pre-training and fo…