114 citations · 475 across the 42 of their papers we have counts for
45 papers
Video Dynamics Prior: An Internal Learning Approach for Robust Video Enhancements
Gaurav Shrivastava, Ser-Nam Lim, Abhinav Shrivastava
In this paper, we present a novel robust framework for low-level vision tasks, including denoising, object removal, frame interpolation, and super-resolution, that does not require…
Towards Scalable Neural Representation for Diverse Videos
Bo He, Xitong Yang, Hanyu Wang +6
Implicit neural representations (INR) have gained increasing attention in representing 3D scenes and images, and have been recently applied to encode videos (e.g., NeRV, E-NeRV). W…
Unifying Tracking and Image-Video Object Detection
Peirong Liu, Rui Wang, Pengchuan Zhang +6
Objection detection (OD) has been one of the most fundamental tasks in computer vision. Recent developments in deep learning have pushed the performance of image OD to new heights…
Totems: Physical Objects for Verifying Visual Integrity
Jingwei Ma, Lucy Chai, Minyoung Huh +4
We introduce a new approach to image forensics: placing physical refractive objects, which we call totems, into a scene so as to protect any photograph taken of that scene. Totems…
ObjectFormer for Image Manipulation Detection and Localization
Junke Wang, Zuxuan Wu, Jingjing Chen +4
Recent advances in image editing techniques have posed serious challenges to the trustworthiness of multimedia data, which drives the research of image tampering detection. In this…
Rethinking Nearest Neighbors for Visual Classification
Menglin Jia, Bor-Chun Chen, Zuxuan Wu +3
Neural network classifiers have become the de-facto choice for current "pre-train then fine-tune" paradigms of visual classification. In this paper, we investigate k-Nearest-Neighb…
Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
Derek Lim, Felix Hohne, Xiuyu Li +4
Many widely used datasets for graph machine learning tasks have generally been homophilous, where nodes with similar labels connect to each other. Recently, new Graph Neural Networ…
A Frequency Perspective of Adversarial Robustness
Shishira R Maiya, Max Ehrlich, Vatsal Agarwal +3
Adversarial examples pose a unique challenge for deep learning systems. Despite recent advances in both attacks and defenses, there is still a lack of clarity and consensus in the…
NeRV: Neural Representations for Videos
Hao Chen, Bo He, Hanyu Wang +3
We propose a novel neural representation for videos (NeRV) which encodes videos in neural networks. Unlike conventional representations that treat videos as frame sequences, we rep…
MixNorm: Test-Time Adaptation Through Online Normalization Estimation
Xuefeng Hu, Gokhan Uzunbas, Sirius Chen +4
We present a simple and effective way to estimate the batch-norm statistics during test time, to fast adapt a source model to target test samples. Known as Test-Time Adaptation, mo…
Robustness and Generalization via Generative Adversarial Training
Omid Poursaeed, Tianxing Jiang, Harry Yang +2
While deep neural networks have achieved remarkable success in various computer vision tasks, they often fail to generalize to new domains and subtle variations of input images. Se…
Equivariant Manifold Flows
Isay Katsman, Aaron Lou, Derek Lim +3
Tractably modelling distributions over manifolds has long been an important goal in the natural sciences. Recent work has focused on developing general machine learning models to l…
Edge Proposal Sets for Link Prediction
Abhay Singh, Qian Huang, Sijia Linda Huang +4
Graphs are a common model for complex relational data such as social networks and protein interactions, and such data can evolve over time (e.g., new friendships) and be noisy (e.g…
Deep Video Inpainting Detection
Peng Zhou, Ning Yu, Zuxuan Wu +3
This paper studies video inpainting detection, which localizes an inpainted region in a video both spatially and temporally. In particular, we introduce VIDNet, Video Inpainting De…
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,…