UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation
Reviewed by Pithpith:FSC2B5U3open to challenge →
read the original abstract
With the recent success of the pre-training technique for NLP and image-linguistic tasks, some video-linguistic pre-training works are gradually developed to improve video-text related downstream tasks. However, most of the existing multimodal models are pre-trained for understanding tasks, leading to a pretrain-finetune discrepancy for generation tasks. This paper proposes UniVL: a Unified Video and Language pre-training model for both multimodal understanding and generation. It comprises four components, including two single-modal encoders, a cross encoder, and a decoder with the Transformer backbone. Five objectives, including video-text joint, conditioned masked language model (CMLM), conditioned masked frame model (CMFM), video-text alignment, and language reconstruction, are designed to train each of the components. We further develop two pre-training strategies, stage by stage pre-training (StagedP) and enhanced video representation (EnhancedV), to make the training process of the UniVL more effective. The pre-train is carried out on a sizeable instructional video dataset HowTo100M. Experimental results demonstrate that the UniVL can learn strong video-text representation and achieves state-of-the-art results on five downstream tasks.
This paper has not been read by Pith yet.
Forward citations
Cited by 8 Pith papers
-
InstrAct: Towards Action-Centric Understanding in Instructional Videos
InstrAction pretrains video foundation models using action-centric data filtering, hard negatives, an Action Perceiver module, DTW-Align, and Masked Action Modeling to reduce static bias and outperform prior models on...
-
Stitch-a-Demo: Video Demonstrations from Multistep Descriptions
Stitch-a-Demo is a retrieval-based method that assembles visually coherent video demonstrations from multistep textual descriptions by training on weakly supervised procedural data with hard negatives.
-
Flamingo: a Visual Language Model for Few-Shot Learning
Flamingo models reach new state-of-the-art few-shot results on image and video tasks by bridging frozen vision and language models with cross-attention layers trained on interleaved web-scale data.
-
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
LanguageBind aligns video, infrared, depth, and audio to a frozen language encoder via contrastive learning on the new VIDAL-10M dataset, extending video-language pretraining to N modalities.
-
Demystifying CLIP Data
MetaCLIP curates balanced 400M-pair subsets from CommonCrawl that outperform CLIP data, reaching 70.8% zero-shot ImageNet accuracy on ViT-B versus CLIP's 68.3%.
-
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
-
GIT: A Generative Image-to-text Transformer for Vision and Language
GIT achieves new state-of-the-art results on 12 vision-language benchmarks, including surpassing human performance on TextCaps, via a simplified single-encoder single-decoder transformer scaled on large pre-training data.
-
Recent Advances in Multimodal Affective Computing: An NLP Perspective
Survey organizing multimodal affective computing research around four NLP tasks, method paradigms, datasets, evaluation protocols, and future directions while releasing a resource repository.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.