Search Results for author:
Found 10 papers, 7 papers with code
Order-preserving Consistency Regularization for Domain Adaptation and Generalization
To alleviate this problem, data augmentation coupled with consistency regularization are commonly adopted to make the model less sensitive to domain-specific attributes.
ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion
Furthermore, we introduce a task-guided diffusion process within the prototype space, enabling the meta-learning of a generative process that transitions from a vanilla prototype to an overfitted prototype.
Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization
By simulating different tubelet motions and applying transformations, such as scaling and rotation, we introduce motion patterns beyond what is present in the pretraining data.
How Severe is Benchmark-Sensitivity in Video Self-Supervised Learning?
Despite the recent success of video self-supervised learning models, there is much still to be understood about their generalization capability.
Frequency-Supervised MR-to-CT Image Synthesis
In this paper, we find that all existing approaches share a common limitation: reconstruction breaks down in and around the high-frequency parts of CT images.
Learning to Learn Kernels with Variational Random Features
We propose meta variational random features (MetaVRF) to learn adaptive kernels for the base-learner, which is developed in a latent variable model by treating the random feature basis as the latent variable.
The ActivityNet Large-Scale Activity Recognition Challenge 2018 Summary
The guest tasks focused on complementary aspects of the activity recognition problem at large scale and involved three challenging and recently compiled datasets: the Kinetics-600 dataset from Google DeepMind, the AVA dataset from Berkeley and Google, and the Moments in Time dataset from MIT and IBM Research.
Guess Where? Actor-Supervision for Spatiotemporal Action Localization
Second, we propose an actor-based attention mechanism that enables the localization of the actions from action class labels and actor proposals and is end-to-end trainable.
ActivityNet Challenge 2017 Summary
The ActivityNet Large Scale Activity Recognition Challenge 2017 Summary: results and challenge participants papers.
Online Action Detection
Third, the start of the action is unknown, so it is unclear over what time window the information should be integrated.
