Related papers: DCT-Mask: Discrete Cosine Transform Mask Represent…

In this paper, we propose a novel encoder-decoder neural network model referred to as DeepBinaryMask for video compressive sensing. In video compressive sensing one frame is acquired using a set of coded masks (sensing matrix) from which a…

Recent approaches for segmentation have leveraged pretrained generative models as feature extractors, treating segmentation as a downstream adaptation task via indirect feature retrieval. This implicit use suffers from a fundamental…

The attributes of object contours has great significance for instance segmentation task. However, most of the current popular deep neural networks do not pay much attention to the object edge information. Inspired by the human annotation…

Frequency domain processing, and in particular the use of Modified Discrete Cosine Transform (MDCT), is the most widespread approach to audio coding. However, at low bitrates, audio quality, especially for speech, degrades drastically due…

Image segmentation remains a challenging task in computer vision, demanding robust mask generation and precise classification. Recent mask-based approaches yield high-quality masks by capturing global context. However, accurately…

This paper presents SimMIM, a simple framework for masked image modeling. We simplify recently proposed related approaches without special designs such as block-wise masking and tokenization via discrete VAE or clustering. To study what let…

While recent neural codecs achieve strong performance at low bitrates when optimized for perceptual quality, their effectiveness deteriorates significantly under ultra-low bitrate conditions. To mitigate this, generative compression methods…

In this paper, we propose the differentiable mask-matching network (DMM-Net) for solving the video object segmentation problem where the initial object masks are provided. Relying on the Mask R-CNN backbone, we extract mask proposals per…

Cell-level dense prediction is central to computational pathology, but remains challenging due to fine-grained histological structures, strong domain shifts, and costly dense annotations. Existing ViT-based pathology foundation models rely…

Conditional coding has lately emerged as the mainstream approach to learned video compression. However, a recent study shows that it may perform worse than residual coding when the information bottleneck arises. Conditional residual coding…

Speech enhancement algorithms based on deep learning have been improved in terms of speech intelligibility and perceptual quality greatly. Many methods focus on enhancing the amplitude spectrum while reconstructing speech using the mixture…

We present a mask-piloted Transformer which improves masked-attention in Mask2Former for image segmentation. The improvement is based on our observation that Mask2Former suffers from inconsistent mask predictions between consecutive decoder…

Anticipating future events is an important prerequisite towards intelligent behavior. Video forecasting has been studied as a proxy task towards this goal. Recent work has shown that to predict semantic segmentation of future frames,…

Most recent transformer-based models show impressive performance on vision tasks, even better than Convolution Neural Networks (CNN). In this work, we present a novel, flexible, and effective transformer-based model for high-quality…

Low-resolution image segmentation is crucial in real-world applications such as robotics, augmented reality, and large-scale scene understanding, where high-resolution data is often unavailable due to computational constraints. To address…

This paper introduces a new fast algorithm for the 8-point discrete cosine transform (DCT) based on the summation-by-parts formula. The proposed method converts the DCT matrix into an alternative transformation matrix that can be decomposed…

An orthogonal 16-point approximate discrete cosine transform (DCT) is introduced. The proposed transform requires neither multiplications nor bit-shifting operations. A fast algorithm based on matrix factorization is introduced, requiring…

Recent trends show recognition accuracy increasing even more profoundly. Inference process of Deep Convolutional Neural Networks (DCNN) has a large number of parameters, requires a large amount of computation, and can be very slow. The…

This paper studies the cosine as basis function for the approximation of univariate and continuous functions without memory. This work studies a supervised learning to obtain the approximation coefficients, instead of using the Discrete…

Neural representations have emerged as a new paradigm for applications in rendering, imaging, geometric modeling, and simulation. Compared to traditional representations such as meshes, point clouds, or volumes they can be flexibly…