相关论文: Learning Long-form Video Prior via Generative Pre-…

Various stuff and things in visual data possess specific traits, which can be learned by deep neural networks and are implicitly represented as the visual prior, e.g., object location and shape, in the model. Such prior potentially impacts…

Recent video and language pretraining frameworks lack the ability to generate sentences. We present Multimodal Video Generative Pretraining (MV-GPT), a new pretraining framework for learning from unlabelled videos which can be effectively…

Video matting has traditionally been limited by the lack of high-quality ground-truth data. Most existing video matting datasets provide only human-annotated imperfect alpha and foreground annotations, which must be composited to background…

GPT has shown its remarkable success in natural language processing. However, the language sequence is not sufficient to describe spatial-temporal details in the visual world. Alternatively, the video sequence is good at capturing such…

Convolutional video models have an order of magnitude larger computational complexity than their counterpart image-level models. Constrained by computational resources, there is no model or training method that can train long video…

In this work, we introduce Vision-Language Generative Pre-trained Transformer (VL-GPT), a transformer model proficient at concurrently perceiving and generating visual and linguistic data. VL-GPT achieves a unified pre-training approach for…

Generating video frames that accurately predict future world states is challenging. Existing approaches either fail to capture the full distribution of outcomes, or yield blurry generations, or both. In this paper we introduce an…

Large-scale pretrained transformers have created milestones in text (GPT-3) and text-to-image (DALL-E and CogView) generation. Its application to video generation is still facing many challenges: The potential huge computation cost makes…

Video-Text pre-training aims at learning transferable representations from large-scale video-text pairs via aligning the semantics between visual and textual information. State-of-the-art approaches extract visual features from raw pixels…

In light of recent advances in multimodal Large Language Models (LLMs), there is increasing attention to scaling them from image-text data to more informative real-world videos. Compared to static images, video poses unique challenges for…

Recent developments in Large Language Models pre-trained on extensive corpora have shown significant success in various natural language processing tasks with minimal fine-tuning. This success offers new promise for robotics, which has long…

This paper addresses key challenges in object-centric representation learning of video. While existing approaches struggle with complex scenes, we propose a novel weakly-supervised framework that emphasises geometric understanding and…

Learning interpretable representations of visual data is an important challenge, to make machines' decisions understandable to humans and to improve generalisation outside of the training distribution. To this end, we propose a deep…

Transformers have been successful for many natural language processing tasks. However, applying transformers to the video domain for tasks such as long-term video generation and scene understanding has remained elusive due to the high…

There are many forms of feature information present in video data. Principle among them are object identity information which is largely static across multiple video frames, and object pose and style information which continuously…

Traditional video summarization methods generate fixed video representations regardless of user interest. Therefore such methods limit users' expectations in content search and exploration scenarios. Multi-modal video summarization is one…

Compared to the prosperity of pre-training models in natural image understanding, the research on large-scale pre-training models for facial knowledge learning is still limited. Current approaches mainly rely on manually assembled and…

Pre-trained models learn general representations from large datsets which can be fine-turned for specific tasks to significantly reduce training time. Pre-trained models like generative pretrained transformers (GPT), bidirectional encoder…

This paper focuses on building object-centric representations for long-term action anticipation in videos. Our key motivation is that objects provide important cues to recognize and predict human-object interactions, especially when the…

Autoregressive transformers have shown remarkable success in video generation. However, the transformers are prohibited from directly learning the long-term dependency in videos due to the quadratic complexity of self-attention, and…