Picture for Loris Bazzani

Loris Bazzani

LatteCLIP: Unsupervised CLIP Fine-Tuning via LMM-Synthetic Texts

Add code
Oct 10, 2024
Viaarxiv icon

ViewFusion: Towards Multi-View Consistency via Interpolated Denoising

Add code
Feb 29, 2024
Viaarxiv icon

iEdit: Localised Text-guided Image Editing with Weak Supervision

Add code
May 10, 2023
Viaarxiv icon

Contrastive Language-Action Pre-training for Temporal Localization

Add code
Apr 26, 2022
Figure 1 for Contrastive Language-Action Pre-training for Temporal Localization
Figure 2 for Contrastive Language-Action Pre-training for Temporal Localization
Figure 3 for Contrastive Language-Action Pre-training for Temporal Localization
Figure 4 for Contrastive Language-Action Pre-training for Temporal Localization
Viaarxiv icon

Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning

Add code
Mar 24, 2021
Figure 1 for Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning
Figure 2 for Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning
Figure 3 for Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning
Figure 4 for Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning
Viaarxiv icon

Image Captioning as Neural Machine Translation Task in SOCKEYE

Add code
Oct 15, 2018
Figure 1 for Image Captioning as Neural Machine Translation Task in SOCKEYE
Figure 2 for Image Captioning as Neural Machine Translation Task in SOCKEYE
Figure 3 for Image Captioning as Neural Machine Translation Task in SOCKEYE
Figure 4 for Image Captioning as Neural Machine Translation Task in SOCKEYE
Viaarxiv icon

Recurrent Mixture Density Network for Spatiotemporal Visual Attention

Add code
Feb 11, 2017
Figure 1 for Recurrent Mixture Density Network for Spatiotemporal Visual Attention
Figure 2 for Recurrent Mixture Density Network for Spatiotemporal Visual Attention
Figure 3 for Recurrent Mixture Density Network for Spatiotemporal Visual Attention
Figure 4 for Recurrent Mixture Density Network for Spatiotemporal Visual Attention
Viaarxiv icon

Kernel Methods on Approximate Infinite-Dimensional Covariance Operators for Image Classification

Add code
Sep 29, 2016
Figure 1 for Kernel Methods on Approximate Infinite-Dimensional Covariance Operators for Image Classification
Figure 2 for Kernel Methods on Approximate Infinite-Dimensional Covariance Operators for Image Classification
Figure 3 for Kernel Methods on Approximate Infinite-Dimensional Covariance Operators for Image Classification
Figure 4 for Kernel Methods on Approximate Infinite-Dimensional Covariance Operators for Image Classification
Viaarxiv icon

Self-taught Object Localization with Deep Networks

Add code
Feb 02, 2016
Figure 1 for Self-taught Object Localization with Deep Networks
Figure 2 for Self-taught Object Localization with Deep Networks
Figure 3 for Self-taught Object Localization with Deep Networks
Figure 4 for Self-taught Object Localization with Deep Networks
Viaarxiv icon

A Unifying Framework in Vector-valued Reproducing Kernel Hilbert Spaces for Manifold Regularization and Co-Regularized Multi-view Learning

Add code
Mar 17, 2015
Figure 1 for A Unifying Framework in Vector-valued Reproducing Kernel Hilbert Spaces for Manifold Regularization and Co-Regularized Multi-view Learning
Figure 2 for A Unifying Framework in Vector-valued Reproducing Kernel Hilbert Spaces for Manifold Regularization and Co-Regularized Multi-view Learning
Figure 3 for A Unifying Framework in Vector-valued Reproducing Kernel Hilbert Spaces for Manifold Regularization and Co-Regularized Multi-view Learning
Figure 4 for A Unifying Framework in Vector-valued Reproducing Kernel Hilbert Spaces for Manifold Regularization and Co-Regularized Multi-view Learning
Viaarxiv icon