Picture for Fanyi Xiao

Fanyi Xiao

Gen2Det: Generate to Detect

Add code
Dec 07, 2023
Viaarxiv icon

Diversify, Don't Fine-Tune: Scaling Up Visual Recognition Training with Synthetic Images

Add code
Dec 04, 2023
Viaarxiv icon

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

Add code
Dec 01, 2023
Viaarxiv icon

EgoObjects: A Large-Scale Egocentric Dataset for Fine-Grained Object Understanding

Add code
Sep 15, 2023
Viaarxiv icon

Exploring Open-Vocabulary Semantic Segmentation without Human Labels

Add code
Jun 01, 2023
Viaarxiv icon

Going Denser with Open-Vocabulary Part Segmentation

Add code
May 18, 2023
Viaarxiv icon

3rd Continual Learning Workshop Challenge on Egocentric Category and Instance Level Object Understanding

Add code
Dec 13, 2022
Viaarxiv icon

SCVRL: Shuffled Contrastive Video Representation Learning

Add code
May 24, 2022
Figure 1 for SCVRL: Shuffled Contrastive Video Representation Learning
Figure 2 for SCVRL: Shuffled Contrastive Video Representation Learning
Figure 3 for SCVRL: Shuffled Contrastive Video Representation Learning
Figure 4 for SCVRL: Shuffled Contrastive Video Representation Learning
Viaarxiv icon

Hierarchical Self-supervised Representation Learning for Movie Understanding

Add code
Apr 06, 2022
Figure 1 for Hierarchical Self-supervised Representation Learning for Movie Understanding
Figure 2 for Hierarchical Self-supervised Representation Learning for Movie Understanding
Figure 3 for Hierarchical Self-supervised Representation Learning for Movie Understanding
Figure 4 for Hierarchical Self-supervised Representation Learning for Movie Understanding
Viaarxiv icon

MoDist: Motion Distillation for Self-supervised Video Representation Learning

Add code
Jun 17, 2021
Figure 1 for MoDist: Motion Distillation for Self-supervised Video Representation Learning
Figure 2 for MoDist: Motion Distillation for Self-supervised Video Representation Learning
Figure 3 for MoDist: Motion Distillation for Self-supervised Video Representation Learning
Figure 4 for MoDist: Motion Distillation for Self-supervised Video Representation Learning
Viaarxiv icon