Related papers: Extremely low-bitrate Image Compression Semantical…
Existing super-resolution (SR) models primarily focus on restoring local texture details, often neglecting the global semantic information within the scene. This oversight can lead to the omission of crucial semantic details or the…
Large language models (LLMs) generate high-dimensional embeddings that capture rich semantic and syntactic information. However, high-dimensional embeddings exacerbate computational complexity and storage requirements, thereby hindering…
Existing multi-object tracking algorithms typically fail to adequately address the issues in low-quality videos, resulting in a significant decline in tracking performance when image quality deteriorates in real-world scenarios. This…
With the rapid advancement of large language models (LLMs), discrete speech representations have become crucial for integrating speech into LLMs. Existing methods for speech representation discretization rely on a predefined codebook size…
Deep neural networks have achieved remarkable success in computer vision; however, their black-box nature in decision-making limits interpretability and trust, particularly in safety-critical applications. Interpretability is crucial in…
One of the core components of conventional (i.e., non-learned) video codecs consists of predicting a frame from a previously-decoded frame, by leveraging temporal correlations. In this paper, we propose an end-to-end learned system for…
We describe an image compression method, consisting of a nonlinear analysis transformation, a uniform quantizer, and a nonlinear synthesis transformation. The transforms are constructed in three successive stages of convolutional linear…
Compression technology is essential for efficient image transmission and storage. With the rapid advances in deep learning, images are beginning to be used for image recognition as well as for human vision. For this reason, research has…
Retrieving accurate semantic information in challenging high dynamic range (HDR) and high-speed conditions remains an open challenge for image-based algorithms due to severe image degradations. Event cameras promise to address these…
Decompilation transforms low-level program languages (PL) (e.g., binary code) into high-level PLs (e.g., C/C++). It has been widely used when analysts perform security analysis on software (systems) whose source code is unavailable, such as…
High-resolution images for remote sensing applications are often not affordable or accessible, especially when in need of a wide temporal span of recordings. Given the easy access to low-resolution (LR) images from satellites, many remote…
Compression artifacts from standard video codecs often degrade perceptual quality. We propose a lightweight, semantic-aware pre-processing framework that enhances perceptual fidelity by selectively addressing these distortions. Our method…
Image-text retrieval is a central problem for understanding the semantic relationship between vision and language, and serves as the basis for various visual and language tasks. Most previous works either simply learn coarse-grained…
Understanding the core dimensions of conceptual semantics is fundamental to uncovering how meaning is organized in language and the brain. Existing approaches often rely on predefined semantic dimensions that offer only broad…
Compressive imaging is an emerging application of compressed sensing, devoted to acquisition, encoding and reconstruction of images using random projections as measurements. In this paper we propose a novel method to provide a scalable…
This paper proposes a novel Non-Local Attention optmization and Improved Context modeling-based image compression (NLAIC) algorithm, which is built on top of the deep nerual network (DNN)-based variational auto-encoder (VAE) structure. Our…
Learning-based lossy image compression usually involves the joint optimization of rate-distortion performance. Most existing methods adopt spatially invariant bit length allocation and incorporate discrete entropy approximation to constrain…
Modern research in content-based image retrieval systems (CIBR) has become progressively more focused on the richness of human semantics. Several approaches may be used to reduced the 'semantic gap' between the high-level human experience…
Several deep learned lossy compression techniques have been proposed in the recent literature. Most of these are optimized by using either MS-SSIM (multi-scale structural similarity) or MSE (mean squared error) as a loss function.…
Surveillance and security scenarios usually require high efficient facial image compression scheme for face recognition and identification. While either traditional general image codecs or special facial image compression schemes only…