相关论文: Data Collection-free Masked Video Modeling

Observable motion in videos can give rise to the definition of objects moving with respect to the scene. The task of segmenting such moving objects is referred to as motion segmentation and is usually tackled either by aggregating motion…

Given the difficulty of manually annotating motion in video, the current best motion estimation methods are trained with synthetic data, and therefore struggle somewhat due to a train/test gap. Self-supervised methods hold the promise of…

Video diffusion models have advanced rapidly in the recent years as a result of series of architectural innovations (e.g., diffusion transformers) and use of novel training objectives (e.g., flow matching). In contrast, less attention has…

In this paper, we introduce Masked Feature Modelling (MFM), a novel approach for the unsupervised pre-training of a Graph Attention Network (GAT) block. MFM utilizes a pretrained Visual Tokenizer to reconstruct masked features of objects…

Despite significant advances in video synthesis, research into multi-shot video generation remains in its infancy. Even with scaled-up models and massive datasets, the shot transition capabilities remain rudimentary and unstable, largely…

We present Masked Frequency Modeling (MFM), a unified frequency-domain-based approach for self-supervised pre-training of visual models. Instead of randomly inserting mask tokens to the input embeddings in the spatial domain, in this paper,…

Unsupervised multi-object segmentation has shown impressive results on images by utilizing powerful semantics learned from self-supervised pretraining. An additional modality such as depth or motion is often used to facilitate the…

This paper introduces a novel dataset construction pipeline that samples pairs of frames from videos and uses multimodal large language models (MLLMs) to generate editing instructions for training instruction-based image manipulation…

Video generation requires synthesizing consistent and persistent frames with dynamic content over time. This work investigates modeling the temporal relations for composing video with arbitrary length, from a few frames to even infinite,…

In this work, we explore the possibility of using synthetically generated data for video-based gesture recognition with large pre-trained models. We consider whether these models have sufficiently robust and expressive representation spaces…

Event camera, a novel neuromorphic vision sensor, records data with high temporal resolution and wide dynamic range, offering new possibilities for accurate visual representation in challenging scenarios. However, event data is inherently…

This paper addresses the challenge of overfitting in the learning of dynamical systems by introducing a novel approach for the generation of synthetic data, aimed at enhancing model generalization and robustness in scenarios characterized…

Generative adversarial models (GANs) continue to produce advances in terms of the visual quality of still images, as well as the learning of temporal correlations. However, few works manage to combine these two interesting capabilities for…

Recent advances in deep learning have enabled the generation of videos from textual descriptions as well as the prediction of future sequences from input videos. Similarly, in human motion modeling, motions can be generated from text or…

Traditional data masking techniques such as anonymization cannot achieve the expected privacy protection while ensuring data utility for privacy-preserving machine learning. Synthetic data plays an increasingly important role as it…

The growth of global consumption has motivated important applications of deep learning to smart manufacturing and machine health monitoring. In particular, analyzing vibration data offers great potential to extract meaningful insights into…

We introduce the MAsked Generative VIdeo Transformer, MAGVIT, to tackle various video synthesis tasks with a single model. We introduce a 3D tokenizer to quantize a video into spatial-temporal visual tokens and propose an embedding method…

Synthetic data is emerging as a promising solution to the scalability issue of supervised deep learning, especially when real data are difficult to acquire or hard to annotate. Synthetic data generation, however, can itself be prohibitively…

This paper addresses the challenges of data scarcity and high acquisition costs in training robust object detection models for complex industrial environments, such as offshore oil platforms. Data collection in these hazardous settings…

Automating quality inspection with computer vision techniques is often a very data-demanding task. Specifically, supervised deep learning requires a large amount of annotated images for training. In practice, collecting and annotating such…