Search Results for author:
Found 10 papers, 5 papers with code
Multiscale Video Pretraining for Long-Term Activity Forecasting
To alleviate this issue, we propose Multiscale Video Pretraining (MVP), a novel self-supervised pretraining approach that learns robust representations for forecasting by learning to predict contextualized representations of future video clips over multiple timescales.
EgoAdapt: A multi-stream evaluation study of adaptation to real-world egocentric user video
We introduce an evaluation framework that directly exploits the user's data stream with new metrics to measure the adaptation gain over the population model, online generalization, and hindsight performance.
How You Move Your Head Tells What You Do: Self-supervised Video Representation Learning with Egocentric Cameras and IMU Sensors
We are particularly interested in learning egocentric video representations benefiting from the head-motion generated by users' daily activities, which can be easily obtained from IMU sensors embedded in AR/VR devices.
Stochastic Prototype Embeddings
We propose a probabilistic method that treats embeddings as random variables.
Adapted Deep Embeddings: A Synthesis of Methods for k-Shot Inductive Transfer Learning
We hope our results will motivate a unification of research in weight transfer, deep metric learning, and few-shot learning.
Open-Ended Content-Style Recombination Via Leakage Filtering
We present a domain-independent method that permits the open-ended recombination of style of one image with the content of another.
Adapted Deep Embeddings: A Synthesis of Methods for $k$-Shot Inductive Transfer Learning
We hope our results will motivate a unification of research in weight transfer, deep metric learning, and few-shot learning.
Learning Deep Disentangled Embeddings with the F-Statistic Loss
Deep-embedding methods aim to discover representations of a domain that make explicit the domain's class structure and thereby support few-shot learning.
A Survey of Inductive Biases for Factorial Representation-Learning
Supervised inductive biases are constraints on the representations based on additional information connected to observations.
Learning to Generate Images with Perceptual Similarity Metrics
We propose instead to use a loss function that is better calibrated to human perceptual judgments of image quality: the multiscale structural-similarity score (MS-SSIM).
