相关论文: Extending Video Masked Autoencoders to 128 frames

An important challenge in emotion recognition is to develop methods that can leverage unlabeled training data. In this paper, we propose the VQ-MAE-AV model, a self-supervised multimodal model that leverages masked autoencoders to learn…

Despite advanced token compression techniques, existing multimodal large language models (MLLMs) still struggle with hour-long video understanding. In this work, we propose Video-XL-Pro, an efficient method for extremely long video…

Existing video Variational Autoencoders (VAEs) generally overlook the similarity between frame contents, leading to redundant latent modeling. In this paper, we propose decoupled VAE (DeCo-VAE) to achieve compact latent representation.…

Establishing correspondence between images or scenes is a significant challenge in computer vision, especially given occlusions, viewpoint changes, and varying object appearances. In this paper, we present Siamese Masked Autoencoders…

Efficient video tokenization remains a key bottleneck in learning general purpose vision models that are capable of processing long video sequences. Prevailing approaches are restricted to encoding videos to a fixed number of tokens, where…

Large Multimodal Models (LMMs) have shown significant visual reasoning capabilities by connecting a visual encoder and a large language model. LMMs typically take in a fixed and large amount of visual tokens, such as the penultimate layer…

We investigated the adaptation and performance of Masked Autoencoders (MAEs) with Vision Transformer (ViT) architectures for self-supervised representation learning on one-dimensional (1D) ultrasound signals. Although MAEs have demonstrated…

We propose an efficient abnormal event detection model based on a lightweight masked auto-encoder (AE) applied at the video frame level. The novelty of the proposed model is threefold. First, we introduce an approach to weight tokens based…

In recent years, the field of learned video compression has witnessed rapid advancement, exemplified by the latest neural video codecs DCVC-DC that has outperformed the upcoming next-generation codec ECM in terms of compression ratio.…

The proliferation of deep learning-based machine vision applications has given rise to a new type of compression, so called video coding for machine (VCM). VCM differs from traditional video coding in that it is optimized for machine vision…

Despite the success of transformers on various computer vision tasks, they suffer from excessive memory and computational cost. Some works present dynamic vision transformers to accelerate inference by pruning redundant tokens. A key to…

Masked image modeling (MIM) has achieved promising results on various vision tasks. However, the limited discriminability of learned representation manifests there is still plenty to go for making a stronger vision learner. Towards this…

Large Vision-Language Models (VLMs) have been extended to understand both images and videos. Visual token compression is leveraged to reduce the considerable token length of visual inputs. To meet the needs of different tasks, existing…

In this paper, we propose Language-Guided Contrastive Audio-Visual Masked Autoencoders (LG-CAV-MAE) to improve audio-visual representation learning. LG-CAV-MAE integrates a pretrained text encoder into contrastive audio-visual masked…

Medical image segmentation remains a formidable challenge due to the label scarcity. Pre-training Vision Transformer (ViT) through masked image modeling (MIM) on large-scale unlabeled medical datasets presents a promising solution,…

The past few years have witnessed increasing interests in applying deep learning to video compression. However, the existing approaches compress a video frame with only a few number of reference frames, which limits their ability to fully…

Autoregressive (AR) video generative models rely on video tokenizers that compress pixels into discrete token sequences. The length of these token sequences is crucial for balancing reconstruction quality against downstream generation…

This paper studies masked autoencoder (MAE) video pre-training for various temporal matching-based downstream tasks, i.e., object-level tracking tasks including video object tracking (VOT) and video object segmentation (VOS),…

Variational AutoEncoders (VAE) employ deep learning models to learn a continuous latent z-space that is subjacent to a high-dimensional observed dataset. With that, many tasks are made possible, including face reconstruction and face…

Pre-training strategies based on self-supervised learning (SSL) have proven to be effective pretext tasks for many downstream tasks in computer vision. Due to the significant disparity between medical and natural images, the application of…