Search Results for author:
Found 5 papers, 4 papers with code
Multi-entity Video Transformers for Fine-Grained Video Representation Learning
In this work, we advance the state-of-the-art for this area by re-examining the design of transformer architectures for video representation learning.
Online Backfilling with No Regret for Large-Scale Image Retrieval
Backfilling is the process of re-extracting all gallery embeddings from upgraded models in image retrieval systems.
BT^2: Backward-compatible Training with Basis Transformation
In this way, the new representation can be directly compared with the old representation, in principle avoiding the need for any backfilling.
$BT^2$: Backward-compatible Training with Basis Transformation
In this way, the new representation can be directly compared with the old representation, in principle avoiding the need for any backfilling.
Spartan: Differentiable Sparsity via Regularized Transportation
We present Spartan, a method for training sparse neural network models with a predetermined level of sparsity.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
