Related papers: InternVideo-Next: Towards General Video Foundation…

Video prediction models often combine three components: an encoder from pixel space to a small latent space, a latent space prediction model, and a generative model back to pixel space. However, the large and unpredictable pixel space makes…

The standard way of training video models entails sampling at each iteration a single clip from a video and optimizing the clip prediction with respect to the video-level label. We argue that a single clip may not have enough temporal…

Video captioning has been a challenging and significant task that describes the content of a video clip in a single sentence. The model of video captioning is usually an encoder-decoder. We find that the normalization of extracted video…

Building state-of-the-art Vision-Language Models (VLMs) with strong captioning capabilities typically necessitates training on billions of high-quality image-text pairs, requiring millions of GPU hours. This paper introduces the…

While recent large-scale video-language pre-training made great progress in video question answering, the design of spatial modeling of video-language models is less fine-grained than that of image-language models; existing practices of…

Scaling general-purpose manipulation to new robot embodiments remains challenging: each platform typically needs large, homogeneous demonstrations, and end-to-end pixel-to-action pipelines may degenerate under background and viewpoint…

The ability to predict future visual observations conditioned on past observations and motor commands can enable embodied agents to plan solutions to a variety of tasks in complex environments. This work shows that we can create good video…

Various contextual information has been employed by many approaches for visual detection tasks. However, most of the existing approaches only focus on specific context for specific tasks. In this paper, GMC, a general framework is proposed…

Large Multimodal Models (LMMs) such as LLaVA are typically trained with an autoregressive language modeling objective, providing only indirect supervision to visual tokens. This often yields weak internal visual representations and brittle…

We present Perceiver-VL, a vision-and-language framework that efficiently handles high-dimensional multimodal inputs such as long videos and text. Powered by the iterative latent cross-attention of Perceiver, our framework scales with…

To build scalable models for challenging real-world tasks, it is important to learn from diverse, multi-modal data in various forms (e.g., videos, text, and images). Among the existing works, a plethora of them have focused on leveraging…

We propose Unicoder-VL, a universal encoder that aims to learn joint representations of vision and language in a pre-training manner. Borrow ideas from cross-lingual pre-trained models, such as XLM and Unicoder, both visual and linguistic…

As a novel video representation method, Neural Representations for Videos (NeRV) has shown great potential in the fields of video compression, video restoration, and video interpolation. In the process of representing videos using NeRV,…

Despite advancements in generating visually stunning content, video diffusion models (VDMs) often yield physically inconsistent results due to pixel-only reconstruction. To address this, we propose MMPhysVideo, the first framework to scale…

Video generation has achieved remarkable progress with the introduction of diffusion models, which have significantly improved the quality of generated videos. However, recent research has primarily focused on scaling up model training,…

This paper proposes a method for performing continual learning of predictive models that facilitate the inference of future frames in video sequences. For a first given experience, an initial Variational Autoencoder, together with a set of…

Self-supervised pre-training paradigms have been extensively explored in the field of skeleton-based action recognition. In particular, methods based on masked prediction have pushed the performance of pre-training to a new height. However,…

We introduce a new encoder-decoder GAN model, FutureGAN, that predicts future frames of a video sequence conditioned on a sequence of past frames. During training, the networks solely receive the raw pixel values as an input, without…

In the past decade, image foundation models (IFMs) have achieved unprecedented progress. However, the potential of directly using IFMs for video self-supervised representation learning has largely been overlooked. In this study, we propose…

We present Omni-Video 2, a scalable and computationally efficient model that connects pretrained multimodal large-language models (MLLMs) with video diffusion models for unified video generation and editing. Our key idea is to exploit the…