activity
20122022
most citedUCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild

4.4k citations · 4.6k across the 11 of their papers we have counts for

collaborators

21 papers

cs.RO20221 cited

PALMER: Perception-Action Loop with Memory for Long-Horizon Planning

Onur Beker, Mohammad Mohammadi, Amir Zamir

To achieve autonomy in a priori unknown real-world scenarios, agents should be able to: i) act from high-dimensional sensory observations (e.g., images), ii) learn from past experi…

cs.LG20221 cited

Task Discovery: Finding the Tasks that Neural Networks Generalize on

Andrei Atanov, Andrei Filatov, Teresa Yeo +2

When developing deep learning models, we usually decide what task we want to solve then search for a model that generalizes well on the task. An intriguing question would be: what…

cs.CV20224 cited

3D Common Corruptions and Data Augmentation

Oğuzhan Fatih Kar, Teresa Yeo, Andrei Atanov +1

We introduce a set of image transformations that can be used as corruptions to evaluate the robustness of models as well as data augmentation mechanisms for training neural network…

cs.CV202210 cited

MultiMAE: Multi-modal Multi-task Masked Autoencoders

Roman Bachmann, David Mizrahi, Andrei Atanov +1

We propose a pre-training strategy called Multi-modal Multi-task Masked Autoencoders (MultiMAE). It differs from standard Masked Autoencoding in two key aspects: I) it can optional…

cs.CV20221 cited

Simple Control Baselines for Evaluating Transfer Learning

Andrei Atanov, Shijian Xu, Onur Beker +2

Transfer learning has witnessed remarkable progress in recent years, for example, with the introduction of augmentation-based contrastive self-supervised learning methods. While a…

cs.GR202211 cited

CLIPasso: Semantically-Aware Object Sketching

Yael Vinker, Ehsan Pajouheshgar, Jessica Y. Bo +5

Abstraction is at the heart of sketching due to the simple and minimal nature of line drawings. Abstraction entails identifying the essential visual properties of an object or scen…