Related papers: Vignette: Perceptual Compression for Video Storage…
Spatial resolution adaptation is a technique which has often been employed in video compression to enhance coding efficiency. This approach encodes a lower resolution version of the input video and reconstructs the original resolution…
A compressive sensing method combined with decomposition of a matrix formed with image frames of a surveillance video into low rank and sparse matrices is proposed to segment the background and extract moving objects in a surveillance…
Long-form video understanding is essential for various applications such as video retrieval, summarizing, and question answering. Yet, traditional approaches demand substantial computing power and are often bottlenecked by GPU memory. To…
Currently, video transmission serves not only the Human Visual System (HVS) for viewing but also machine perception for analysis. However, existing codecs are primarily optimized for pixel-domain and HVS-perception metrics rather than the…
Streaming video understanding with large vision-language models (VLMs) requires a compact memory that can support future reasoning over an ever-growing visual history. A common solution is to compress the key-value (KV) cache, but existing…
We propose a novel neural representation for videos (NeRV) which encodes videos in neural networks. Unlike conventional representations that treat videos as frame sequences, we represent videos as neural networks taking frame index as…
Vision agent memory has shown remarkable effectiveness in streaming video understanding. However, storing such memory for videos incurs substantial memory overhead, leading to high costs in both storage and computation. To address this…
In order to be able to deliver today's voluminous amount of video contents through limited bandwidth channels in a perceptually optimal way, it is important to consider perceptual trade-offs of compression and space-time downsampling…
In this paper, we propose a new framework for compressive video sensing (CVS) that exploits the inherent spatial and temporal redundancies of a video sequence, effectively. The proposed method splits the video sequence into the key and…
In the field of neural data compression, the prevailing focus has been on optimizing algorithms for either classical distortion metrics, such as PSNR or SSIM, or human perceptual quality. With increasing amounts of data consumed by machines…
We propose in this paper a new paradigm for facial video compression. We leverage the generative capacity of GANs such as StyleGAN to represent and compress a video, including intra and inter compression. Each frame is inverted in the…
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…
Video compression relies heavily on exploiting the temporal redundancy between video frames, which is usually achieved by estimating and using the motion information. The motion information is represented as optical flows in most of the…
Computer vision has become a popular tool in intelligent transportation systems (ITS), enabling various applications through roadside traffic cameras that capture video and transmit it in real time to computing devices within the same…
Recent years have witnessed an increasing interest in end-to-end learned video compression. Most previous works explore temporal redundancy by detecting and compressing a motion map to warp the reference frame towards the target frame. Yet,…
Video represents the majority of internet traffic today, driving a continual race between the generation of higher quality content, transmission of larger file sizes, and the development of network infrastructure. In addition, the recent…
We propose an end-to-end learned image compression codec wherein the analysis transform is jointly trained with an object classification task. This study affirms that the compressed latent representation can predict human perceptual…
Implicit Neural Networks (INRs) have emerged as powerful representations to encode all forms of data, including images, videos, audios, and scenes. With video, many INRs for video have been proposed for the compression task, and recent…
Vision Transformers (ViTs) have emerged as state-of-the-art models for various vision tasks recently. However, their heavy computation costs remain daunting for resource-limited devices. To address this, researchers have dedicated…
In the last decade, the need for storing videos from cataract surgery has increased significantly. Hospitals continue to improve their imaging and recording devices (e.g., microscopes and cameras used in microscopic surgery, such as…