Picture for Guocheng Niu

Guocheng Niu

UNIMO-2: End-to-End Unified Vision-Language Grounded Learning

Add code
Mar 17, 2022
Figure 1 for UNIMO-2: End-to-End Unified Vision-Language Grounded Learning
Figure 2 for UNIMO-2: End-to-End Unified Vision-Language Grounded Learning
Figure 3 for UNIMO-2: End-to-End Unified Vision-Language Grounded Learning
Figure 4 for UNIMO-2: End-to-End Unified Vision-Language Grounded Learning
Viaarxiv icon

DU-VLG: Unifying Vision-and-Language Generation via Dual Sequence-to-Sequence Pre-training

Add code
Mar 17, 2022
Figure 1 for DU-VLG: Unifying Vision-and-Language Generation via Dual Sequence-to-Sequence Pre-training
Figure 2 for DU-VLG: Unifying Vision-and-Language Generation via Dual Sequence-to-Sequence Pre-training
Figure 3 for DU-VLG: Unifying Vision-and-Language Generation via Dual Sequence-to-Sequence Pre-training
Figure 4 for DU-VLG: Unifying Vision-and-Language Generation via Dual Sequence-to-Sequence Pre-training
Viaarxiv icon

Weakly Supervised Dense Video Captioning via Jointly Usage of Knowledge Distillation and Cross-modal Matching

Add code
May 18, 2021
Figure 1 for Weakly Supervised Dense Video Captioning via Jointly Usage of Knowledge Distillation and Cross-modal Matching
Figure 2 for Weakly Supervised Dense Video Captioning via Jointly Usage of Knowledge Distillation and Cross-modal Matching
Figure 3 for Weakly Supervised Dense Video Captioning via Jointly Usage of Knowledge Distillation and Cross-modal Matching
Figure 4 for Weakly Supervised Dense Video Captioning via Jointly Usage of Knowledge Distillation and Cross-modal Matching
Viaarxiv icon

UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning

Add code
Dec 31, 2020
Figure 1 for UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning
Figure 2 for UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning
Figure 3 for UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning
Figure 4 for UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning
Viaarxiv icon