相关论文: VideoMaMa: Mask-Guided Video Matting via Generativ…

Image matching is a fundamental computer vision problem. While learning-based methods achieve state-of-the-art performance on existing benchmarks, they generalize poorly to in-the-wild images. Such methods typically need to train separate…

Embodied world models have emerged as a promising paradigm in robotics, most of which leverage large-scale Internet videos or pretrained video generation models to enrich visual and motion priors. However, they still face key challenges: a…

Large-scale video generative models are trained on vast and diverse visual data, enabling them to internalize rich structural, semantic, and dynamic priors of the visual world. While these models have demonstrated impressive generative…

Recent methods for visual question answering rely on large-scale annotated datasets. Manual annotation of questions and answers for videos, however, is tedious, expensive and prevents scalability. In this work, we propose to avoid manual…

The recent advancements in Generative Adversarial Networks (GANs) and the emergence of Diffusion models have significantly streamlined the production of highly realistic and widely accessible synthetic content. As a result, there is a…

Discrete video tokenization is essential for efficient autoregressive generative modeling due to the high dimensionality of video data. This work introduces a state-of-the-art discrete video tokenizer with two key contributions. First, we…

We present a domain adaptation of video diffusion models to generate highly realistic time-lapse microscopy videos of cell division in HeLa cells. Although state-of-the-art generative video models have advanced significantly for natural…

Surgical video segmentation is a critical task in computer-assisted surgery, essential for enhancing surgical quality and patient outcomes. Recently, the Segment Anything Model 2 (SAM2) framework has demonstrated remarkable advancements in…

We explore the potential of large-scale generative video models for autonomous driving, introducing an open-source auto-regressive video model (VaViM) and its companion video-action model (VaVAM) to investigate how video pre-training…

Synthesizing realistic videos according to a given speech is still an open challenge. Previous works have been plagued by issues such as inaccurate lip shape generation and poor image quality. The key reason is that only motions and…

State-of-the-art video action classifiers often suffer from overfitting. They tend to be biased towards specific objects and scene cues, rather than the foreground action content, leading to sub-optimal generalization performances. Recent…

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…

Video action understanding tasks in real-world scenarios always suffer data limitations. In this paper, we address the data-limited action understanding problem by bridging data scarcity. We propose a novel method that employs a…

Subject-to-video generation has witnessed substantial progress in recent years. However, existing models still face significant challenges in faithfully following textual instructions. This limitation, commonly known as the copy-paste…

The Segmentation Anything Model 2 (SAM2) has proven to be a powerful foundation model for promptable visual object segmentation in both images and videos, capable of storing object-aware memories and transferring them temporally through…

World models, which predict future transitions from past observation and action sequences, have shown great promise for improving data efficiency in sequential decision-making. However, existing world models often require extensive…

Recent endeavors in video editing have showcased promising results in single-attribute editing or style transfer tasks, either by training text-to-video (T2V) models on text-video data or adopting training-free methods. However, when…

Video DiTs have advanced video generation, yet they still struggle to model multi-instance or subject-object interactions. This raises a key question: How do these models internally represent interactions? To answer this, we curate…

Large scale Vision-Language (VL) models have shown tremendous success in aligning representations between visual and text modalities. This enables remarkable progress in zero-shot recognition, image generation & editing, and many other…

We propose a new two-stage pre-training framework for video-to-text generation tasks such as video captioning and video question answering: A generative encoder-decoder model is first jointly pre-trained on massive image-text data to learn…