相关论文: COSA: Concatenated Sample Pretrained Vision-Langua…

We propose a new architecture for adapting a sentence-level sequence-to-sequence transformer by incorporating multiple pretrained document context signals and assess the impact on translation performance of (1) different pretraining…

Recent studies have pointed out that many well-developed Visual Question Answering (VQA) models are heavily affected by the language prior problem, which refers to making predictions based on the co-occurrence pattern between textual…

Controllable video generation has emerged as a versatile tool for autonomous driving, enabling realistic synthesis of traffic scenarios. However, existing methods depend on control signals at inference time to guide the generative model…

The use of complex attention modules has improved the performance of the Visual Question Answering (VQA) task. This work aims to learn an improved multi-modal representation through dense interaction of visual and textual modalities. The…

Vision-language-action models (VLAs) have shown potential in leveraging pretrained vision-language models and diverse robot demonstrations for learning generalizable sensorimotor control. While this paradigm effectively utilizes large-scale…

The combination of visual and textual representations has produced excellent results in tasks such as image captioning and visual question answering, but the inference capabilities of multimodal representations are largely untested. In the…

Modern self-supervised learning algorithms typically enforce persistency of instance representations across views. While being very effective on learning holistic image and video representations, such an objective becomes sub-optimal for…

The foundation models based on pre-training technology have significantly advanced artificial intelligence from theoretical to practical applications. These models have facilitated the feasibility of computer-aided diagnosis for widespread…

Image-text matching plays a central role in bridging vision and language. Most existing approaches only rely on the image-text instance pair to learn their representations, thereby exploiting their matching relationships and making the…

Accurate and efficient Video Quality Assessment (VQA) has long been a key research challenge. Current mainstream VQA methods typically improve performance by pretraining on large-scale classification datasets (e.g., ImageNet, Kinetics-400),…

In the rapidly evolving field of artificial intelligence, multimodal models, e.g., integrating vision and language into visual-language models (VLMs), have become pivotal for many applications, ranging from image captioning to multimodal…

We present a self-supervised learning framework, COCO-LM, that pretrains Language Models by COrrecting and COntrasting corrupted text sequences. Following ELECTRA-style pretraining, COCO-LM employs an auxiliary language model to corrupt…

State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any…

Vision transformers have established a precedent of patchifying images into uniformly-sized chunks before processing. We hypothesize that this design choice may limit models in learning comprehensive and compositional representations from…

Pre-trained vision language models have shown remarkable performance on visual recognition tasks, but they typically assume the availability of complete multimodal inputs during both training and inference. In real-world scenarios, however,…

Large-scale video-language pretraining enables strong generalization across multimodal tasks but often incurs prohibitive computational costs. Although recent advances in masked visual modeling help mitigate this issue, they still suffer…

Continual Learning (CL) enables machine learning models to learn from continuously shifting new training data in absence of data from old tasks. Recently, pretrained vision transformers combined with prompt tuning have shown promise for…

Contrastive Language-Image Pre-training (CLIP) has drawn increasing attention recently for its transferable visual representation learning. However, due to the semantic gap within datasets, CLIP's pre-trained image-text alignment becomes…

Image captioning requires numerous annotated image-text pairs, resulting in substantial annotation costs. Recently, large models (e.g. diffusion models and large language models) have excelled in producing high-quality images and text. This…

Recent text-to-video models have demonstrated strong temporal generation capabilities, yet their potential for image restoration remains underexplored. In this work, we repurpose CogVideo for progressive visual restoration tasks by…