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

We introduce InternVideo2, a new family of video foundation models (ViFM) that achieve the state-of-the-art results in video recognition, video-text tasks, and video-centric dialogue. Our core design is a progressive training approach that…

The foundation models have recently shown excellent performance on a variety of downstream tasks in computer vision. However, most existing vision foundation models simply focus on image-level pretraining and adpation, which are limited for…

Decomposing a video into a layer-based representation is crucial for easy video editing for the creative industries, as it enables independent editing of specific layers. Existing video-layer decomposition models rely on implicit neural…

Most video compression methods focus on human visual perception, neglecting semantic preservation. This leads to severe semantic loss during the compression, hampering downstream video analysis tasks. In this paper, we propose a Masked…

Reinforcement learning based post-training paradigms for Video Large Language Models (VideoLLMs) have achieved significant success by optimizing for visual-semantic tasks such as captioning or VideoQA. However, while these approaches…

The field of advanced text-to-image generation is witnessing the emergence of unified frameworks that integrate powerful text encoders, such as CLIP and T5, with Diffusion Transformer backbones. Although there have been efforts to control…

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 studies have adapted generative Multimodal Large Language Models (MLLMs) into embedding extractors for vision tasks, typically through fine-tuning to produce universal representations. However, their performance on video remains…

We present Recurrent Video Masked-Autoencoders (RVM): a novel approach to video representation learning that leverages recurrent computation to model the temporal structure of video data. RVM couples an asymmetric masking objective with a…

Unified vision-language frameworks have greatly advanced in recent years, most of which adopt an encoder-decoder architecture to unify image-text tasks as sequence-to-sequence generation. However, existing video-language (VidL) models still…

The ultimate goal for foundation models is realizing task-agnostic, i.e., supporting out-of-the-box usage without task-specific fine-tuning. Although breakthroughs have been made in natural language processing and image representation…

In this paper, we present an end-to-end trainable unified multiscale encoder-decoder transformer that is focused on dense prediction tasks in video. The presented Multiscale Encoder-Decoder Video Transformer (MED-VT) uses multiscale…

We present a simplified, task-agnostic multi-modal pre-training approach that can accept either video or text input, or both for a variety of end tasks. Existing pre-training are task-specific by adopting either a single cross-modal encoder…

While Multimodal Large Language Models demonstrate impressive semantic capabilities, they often suffer from spatial blindness, struggling with fine-grained geometric reasoning and physical dynamics. Existing solutions typically rely on…

Most Video-Large Language Models (Video-LLMs) adopt an encoder-decoder framework, where a vision encoder extracts frame-wise features for processing by a language model. However, this approach incurs high computational costs, introduces…

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 prediction is a challenging task. The quality of video frames from current state-of-the-art (SOTA) generative models tends to be poor and generalization beyond the training data is difficult. Furthermore, existing prediction…

While Large Multimodal Models (LMMs) have made significant progress, they remain largely text-centric, relying on language as their core reasoning modality. As a result, they are limited in their ability to handle reasoning tasks that are…

Vision-language pre-training like CLIP has shown promising performance on various downstream tasks such as zero-shot image classification and image-text retrieval. Most of the existing CLIP-alike works usually adopt relatively large image…

Multiview video is a key data source for volumetric video, enabling immersive 3D scene reconstruction but posing significant challenges in storage and transmission due to its massive data volume. Recently, deep learning-based end-to-end…