114 citations · 475 across the 42 of their papers we have counts for
17 papers · 1 filter
GTA: Global Temporal Attention for Video Action Understanding
Bo He, Xitong Yang, Zuxuan Wu +3
Self-attention learns pairwise interactions to model long-range dependencies, yielding great improvements for video action recognition. In this paper, we seek a deeper understandin…
Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
Qian Huang, Horace He, Abhay Singh +2
Graph Neural Networks (GNNs) are the predominant technique for learning over graphs. However, there is relatively little understanding of why GNNs are successful in practice and wh…
Analyzing and Mitigating JPEG Compression Defects in Deep Learning
Max Ehrlich, Larry Davis, Ser-Nam Lim +1
With the proliferation of deep learning methods, many computer vision problems which were considered academic are now viable in the consumer setting. One drawback of consumer appli…
Intentonomy: a Dataset and Study towards Human Intent Understanding
Menglin Jia, Zuxuan Wu, Austin Reiter +3
An image is worth a thousand words, conveying information that goes beyond the physical visual content therein. In this paper, we study the intent behind social media images with a…
What makes fake images detectable? Understanding properties that generalize
Lucy Chai, David Bau, Ser-Nam Lim +1
The quality of image generation and manipulation is reaching impressive levels, making it increasingly difficult for a human to distinguish between what is real and what is fake. H…
PyTorch Metric Learning
Kevin Musgrave, Serge Belongie, Ser-Nam Lim
Deep metric learning algorithms have a wide variety of applications, but implementing these algorithms can be tedious and time consuming. PyTorch Metric Learning is an open source…
Curriculum Manager for Source Selection in Multi-Source Domain Adaptation
Luyu Yang, Yogesh Balaji, Ser-Nam Lim +1
The performance of Multi-Source Unsupervised Domain Adaptation depends significantly on the effectiveness of transfer from labeled source domain samples. In this paper, we proposed…
Deep Co-Training with Task Decomposition for Semi-Supervised Domain Adaptation
Luyu Yang, Yan Wang, Mingfei Gao +4
Semi-supervised domain adaptation (SSDA) aims to adapt models trained from a labeled source domain to a different but related target domain, from which unlabeled data and a small s…
Neural Manifold Ordinary Differential Equations
Aaron Lou, Derek Lim, Isay Katsman +4
To better conform to data geometry, recent deep generative modelling techniques adapt Euclidean constructions to non-Euclidean spaces. In this paper, we study normalizing flows on…
Detecting Deep-Fake Videos from Appearance and Behavior
Shruti Agarwal, Tarek El-Gaaly, Hany Farid +1
Synthetically-generated audios and videos -- so-called deep fakes -- continue to capture the imagination of the computer-graphics and computer-vision communities. At the same time,…
Quantization Guided JPEG Artifact Correction
Max Ehrlich, Larry Davis, Ser-Nam Lim +1
The JPEG image compression algorithm is the most popular method of image compression because of its ability for large compression ratios. However, to achieve such high compression,…
One-Shot Domain Adaptation For Face Generation
Chao Yang, Ser-Nam Lim
In this paper, we propose a framework capable of generating face images that fall into the same distribution as that of a given one-shot example. We leverage a pre-trained StyleGAN…
Deep Multi-Modal Sets
Austin Reiter, Menglin Jia, Pu Yang +1
Many vision-related tasks benefit from reasoning over multiple modalities to leverage complementary views of data in an attempt to learn robust embedding spaces. Most deep learning…
A Metric Learning Reality Check
Kevin Musgrave, Serge Belongie, Ser-Nam Lim
Deep metric learning papers from the past four years have consistently claimed great advances in accuracy, often more than doubling the performance of decade-old methods. In this p…
Better Set Representations For Relational Reasoning
Qian Huang, Horace He, Abhay Singh +3
Incorporating relational reasoning into neural networks has greatly expanded their capabilities and scope. One defining trait of relational reasoning is that it operates on a set o…
Differentiating through the Fréchet Mean
Aaron Lou, Isay Katsman, Qingxuan Jiang +3
Recent advances in deep representation learning on Riemannian manifolds extend classical deep learning operations to better capture the geometry of the manifold. One possible exten…
On Feature Normalization and Data Augmentation
Boyi Li, Felix Wu, Ser-Nam Lim +2
The moments (a.k.a., mean and standard deviation) of latent features are often removed as noise when training image recognition models, to increase stability and reduce training ti…