research
∙
03/01/2023
Collage Diffusion
Text-conditional diffusion models generate high-quality, diverse images....
share
research
∙
07/20/2022
Spotting Temporally Precise, Fine-Grained Events in Video
We introduce the task of spotting temporally precise, fine-grained event...
research
∙
04/15/2022
Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning
An ideal learned representation should display transferability and robus...
research
∙
03/24/2022
Shoring Up the Foundations: Fusing Model Embeddings and Weak Supervision
Foundation models offer an exciting new paradigm for constructing models...
research
∙
09/13/2021
Low-Shot Validation: Active Importance Sampling for Estimating Classifier Performance on Rare Categories
For machine learning models trained with limited labeled training data, ...
research
∙
09/03/2021
Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition
Human pose is a useful feature for fine-grained sports action understand...
research
∙
07/01/2021
Mandoline: Model Evaluation under Distribution Shift
Machine learning models are often deployed in different settings than th...
research
∙
03/12/2021
Large Batch Simulation for Deep Reinforcement Learning
We accelerate deep reinforcement learning-based training in visually com...
research
∙
11/21/2020
Iterative Text-based Editing of Talking-heads Using Neural Retargeting
We present a text-based tool for editing talking-head video that enables...
research
∙
08/28/2020
Background Splitting: Finding Rare Classes in a Sea of Background
We focus on the real-world problem of training accurate deep models for ...
research
∙
08/13/2020
Analyzing Who and What Appears in a Decade of US Cable TV News
Cable TV news reaches millions of U.S. households each day, meaning that...
research
∙
08/11/2020
Vid2Player: Controllable Video Sprites that Behave and Appear like Professional Tennis Players
We present a system that converts annotated broadcast video of tennis ma...
research
∙
06/26/2020
Train and You'll Miss It: Interactive Model Iteration with Weak Supervision and Pre-Trained Embeddings
Our goal is to enable machine learning systems to be trained interactive...
research
∙
02/27/2020
Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods
Weak supervision is a popular method for building machine learning model...
research
∙
10/21/2019
Multi-Resolution Weak Supervision for Sequential Data
Since manually labeling training data is slow and expensive, recent indu...
research
∙
10/07/2019
Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels
Many real-world video analysis applications require the ability to ident...
research
∙
12/06/2018
Online Model Distillation for Efficient Video Inference
High-quality computer vision models typically address the problem of und...
research
∙
05/18/2018