Picture for Zhenshan Tan

Zhenshan Tan

A Unified Two-Stage Group Semantics Propagation and Contrastive Learning Network for Co-Saliency Detection

Add code
Aug 13, 2022
Figure 1 for A Unified Two-Stage Group Semantics Propagation and Contrastive Learning Network for Co-Saliency Detection
Figure 2 for A Unified Two-Stage Group Semantics Propagation and Contrastive Learning Network for Co-Saliency Detection
Figure 3 for A Unified Two-Stage Group Semantics Propagation and Contrastive Learning Network for Co-Saliency Detection
Figure 4 for A Unified Two-Stage Group Semantics Propagation and Contrastive Learning Network for Co-Saliency Detection
Viaarxiv icon

Contrastive Cross-Modal Knowledge Sharing Pre-training for Vision-Language Representation Learning and Retrieval

Add code
Jul 08, 2022
Figure 1 for Contrastive Cross-Modal Knowledge Sharing Pre-training for Vision-Language Representation Learning and Retrieval
Figure 2 for Contrastive Cross-Modal Knowledge Sharing Pre-training for Vision-Language Representation Learning and Retrieval
Figure 3 for Contrastive Cross-Modal Knowledge Sharing Pre-training for Vision-Language Representation Learning and Retrieval
Figure 4 for Contrastive Cross-Modal Knowledge Sharing Pre-training for Vision-Language Representation Learning and Retrieval
Viaarxiv icon

UTC: A Unified Transformer with Inter-Task Contrastive Learning for Visual Dialog

Add code
May 03, 2022
Figure 1 for UTC: A Unified Transformer with Inter-Task Contrastive Learning for Visual Dialog
Figure 2 for UTC: A Unified Transformer with Inter-Task Contrastive Learning for Visual Dialog
Figure 3 for UTC: A Unified Transformer with Inter-Task Contrastive Learning for Visual Dialog
Figure 4 for UTC: A Unified Transformer with Inter-Task Contrastive Learning for Visual Dialog
Viaarxiv icon