Search Results for author:
Found 8 papers, 5 papers with code
HOI-Swap: Swapping Objects in Videos with Hand-Object Interaction Awareness
We study the problem of precisely swapping objects in videos, with a focus on those interacted with by hands, given one user-provided reference object image.
Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videos
We investigate exocentric-to-egocentric cross-view translation, which aims to generate a first-person (egocentric) view of an actor based on a video recording that captures the actor from a third-person (exocentric) perspective.
Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
We present Ego-Exo4D, a diverse, large-scale multimodal multiview video dataset and benchmark challenge.
MetaFormer Baselines for Vision
By simply applying depthwise separable convolutions as token mixer in the bottom stages and vanilla self-attention in the top stages, the resulting model CAFormer sets a new record on ImageNet-1K: it achieves an accuracy of 85. 5% at 224x224 resolution, under normal supervised training without external data or distillation.
Ranked #2 on
Domain Generalization
on ImageNet-C
(using extra training data)
MetaFormer Is Actually What You Need for Vision
Based on this observation, we hypothesize that the general architecture of the Transformers, instead of the specific token mixer module, is more essential to the model's performance.
Ranked #9 on
Semantic Segmentation
on DensePASS
No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data
Motivated by the above findings, we propose a novel and simple algorithm called Classifier Calibration with Virtual Representations (CCVR), which adjusts the classifier using virtual representations sampled from an approximated gaussian mixture model.
MetaSelector: Meta-Learning for Recommendation with User-Level Adaptive Model Selection
Recommender systems often face heterogeneous datasets containing highly personalized historical data of users, where no single model could give the best recommendation for every user.
Federated Meta-Learning with Fast Convergence and Efficient Communication
Statistical and systematic challenges in collaboratively training machine learning models across distributed networks of mobile devices have been the bottlenecks in the real-world application of federated learning.
