2.5k citations
- IBM Research - Thomas J. Watson Research CenterUS46 papers
- Massachusetts Institute of TechnologyUS22 papers
- Vassar CollegeUS16 papers
- California Institute of TechnologyUS13 papers
- Columbia UniversityUS12 papers
- Stanford UniversityUS11 papers
- Centre National de la Recherche ScientifiqueFR10 papers
- Carnegie Mellon UniversityUS9 papers
- University of MichiganUS9 papers
- IBM Research - ZurichCH8 papers
- Iowa State UniversityUS8 papers
- Lowell ObservatoryUS8 papers
19 papers · 1 filter
When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?
Lijie Fan, Sijia Liu, Pin-Yu Chen +2
Contrastive learning (CL) can learn generalizable feature representations and achieve the state-of-the-art performance of downstream tasks by finetuning a linear classifier on top…
Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language
Mingyu Ding, Zhenfang Chen, Tao Du +3
In this work, we propose a unified framework, called Visual Reasoning with Differ-entiable Physics (VRDP), that can jointly learn visual concepts and infer physics models of object…
DP-SSL: Towards Robust Semi-supervised Learning with A Few Labeled Samples
Yi Xu, Jiandong Ding, Lu Zhang +1
The scarcity of labeled data is a critical obstacle to deep learning. Semi-supervised learning (SSL) provides a promising way to leverage unlabeled data by pseudo labels. However,…
Quantification of Carbon Sequestration in Urban Forests
Levente J. Klein, Wang Zhou, Conrad M. Albrecht
Vegetation, trees in particular, sequester carbon by absorbing carbon dioxide from the atmosphere. However, the lack of efficient quantification methods of carbon stored in trees r…
Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning
Zhenfang Chen, Jiayuan Mao, Jiajun Wu +3
We study the problem of dynamic visual reasoning on raw videos. This is a challenging problem; currently, state-of-the-art models often require dense supervision on physical object…
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…