中文
相关论文

相关论文: Boosting the Performance of Video Compression Arti…

200 篇论文

We introduce a video compression algorithm based on instance-adaptive learning. On each video sequence to be transmitted, we finetune a pretrained compression model. The optimal parameters are transmitted to the receiver along with the…

图像与视频处理 · 电气工程与系统科学 2023-06-26 Ties van Rozendaal , Johann Brehmer , Yunfan Zhang , Reza Pourreza , Auke Wiggers , Taco S. Cohen

Analog magnetic tapes have been the main video data storage device for several decades. Videos stored on analog videotapes exhibit unique degradation patterns caused by tape aging and reader device malfunctioning that are different from…

计算机视觉与模式识别 · 计算机科学 2023-11-07 Lorenzo Agnolucci , Leonardo Galteri , Marco Bertini , Alberto Del Bimbo

Existing methods for video interpolation heavily rely on deep convolution neural networks, and thus suffer from their intrinsic limitations, such as content-agnostic kernel weights and restricted receptive field. To address these issues, we…

计算机视觉与模式识别 · 计算机科学 2022-03-29 Zhihao Shi , Xiangyu Xu , Xiaohong Liu , Jun Chen , Ming-Hsuan Yang

We present a learning-based framework, recurrent transformer network (RTN), to restore heavily degraded old films. Instead of performing frame-wise restoration, our method is based on the hidden knowledge learned from adjacent frames that…

计算机视觉与模式识别 · 计算机科学 2022-04-01 Ziyu Wan , Bo Zhang , Dongdong Chen , Jing Liao

In the context of long-term video understanding with large multimodal models, many frameworks have been proposed. Although transformer-based visual compressors and memory-augmented approaches are often used to process long videos, they…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Sosuke Yamao , Natsuki Miyahara , Yuankai Qi , Shun Takeuchi

Optimizing video inference efficiency has become increasingly important with the growing demand for video analysis in various fields. Some existing methods achieve high efficiency by explicit discard of spatial or temporal information,…

计算机视觉与模式识别 · 计算机科学 2023-09-18 Rui Deng , Qian Wu , Yuke Li , Haoran Fu

Video object detection is a fundamental problem in computer vision and has a wide spectrum of applications. Based on deep networks, video object detection is actively studied for pushing the limits of detection speed and accuracy. To reduce…

计算机视觉与模式识别 · 计算机科学 2021-03-29 Xinggang Wang , Zhaojin Huang , Bencheng Liao , Lichao Huang , Yongchao Gong , Chang Huang

Event cameras excel at high-speed, low-power, and high-dynamic-range scene perception. However, as they fundamentally record only relative intensity changes rather than absolute intensity, the resulting data streams suffer from a…

计算机视觉与模式识别 · 计算机科学 2026-05-08 Gang Xu , Zhiyu Zhu , Junhui Hou

Though action recognition in videos has achieved great success recently, it remains a challenging task due to the massive computational cost. Designing lightweight networks is a possible solution, but it may degrade the recognition…

计算机视觉与模式识别 · 计算机科学 2020-02-11 Wenhao Wu , Dongliang He , Xiao Tan , Shifeng Chen , Yi Yang , Shilei Wen

Classifying videos into distinct categories, such as Sport and Music Video, is crucial for multimedia understanding and retrieval, especially when an immense volume of video content is being constantly generated. Traditional methods require…

计算机视觉与模式识别 · 计算机科学 2024-03-14 Yuxing Han , Yunan Ding , Chen Ye Gan , Jiangtao Wen

Long-form video understanding presents significant challenges for interactive retrieval systems, as conventional methods struggle to process extensive video content efficiently. Existing approaches often rely on single models, inefficient…

With the widespread of user-generated Internet videos, emotion recognition in those videos attracts increasing research efforts. However, most existing works are based on framelevel visual features and/or audio features, which might fail to…

计算机视觉与模式识别 · 计算机科学 2016-08-04 Haimin Zhang , Min Xu

JPEG is a widely used compression scheme to efficiently reduce the volume of transmitted images. The artifacts appear among blocks due to the information loss, which not only affects the quality of images but also harms the subsequent…

计算机视觉与模式识别 · 计算机科学 2024-01-04 Long Peng , Yang Cao , Yuejin Sun , Yang Wang

The popular VQ-VAE models reconstruct images through learning a discrete codebook but suffer from a significant issue in the rapid quality degradation of image reconstruction as the compression rate rises. One major reason is that a higher…

计算机视觉与模式识别 · 计算机科学 2023-11-07 Xinmiao Lin , Yikang Li , Jenhao Hsiao , Chiuman Ho , Yu Kong

The enhanced Deep Hierarchical Video Compression-DHVC 2.0-has been introduced. This single-model neural video codec operates across a broad range of bitrates, delivering not only superior compression performance to representative methods…

图像与视频处理 · 电气工程与系统科学 2024-10-04 Ming Lu , Zhihao Duan , Wuyang Cong , Dandan Ding , Fengqing Zhu , Zhan Ma

Existing open-source film restoration methods show limited performance compared to commercial methods due to training with low-quality synthetic data and employing noisy optical flows. In addition, high-resolution films have not been…

计算机视觉与模式识别 · 计算机科学 2026-01-01 Rongji Xun , Junjie Yuan , Zhongjie Wang

Current video retrieval systems, especially those used in competitions, primarily focus on querying individual keyframes or images rather than encoding an entire clip or video segment. However, queries often describe an action or event over…

计算机视觉与模式识别 · 计算机科学 2026-04-29 Quoc-Bao Nguyen-Le , Thanh-Huy Le-Nguyen

Deep learning has enabled various Internet of Things (IoT) applications. Still, designing models with high accuracy and computational efficiency remains a significant challenge, especially in real-time video processing applications. Such…

计算机视觉与模式识别 · 计算机科学 2023-05-12 Hadjer Benmeziane , Halima Bouzidi , Hamza Ouarnoughi , Ozcan Ozturk , Smail Niar

Image Representation learning via input reconstruction is a common technique in machine learning for generating representations that can be effectively utilized by arbitrary downstream tasks. A well-established approach is using…

神经与进化计算 · 计算机科学 2025-06-10 Raoof HojatJalali , Edmondo Trentin

This work proposes a hybrid, explicit-implicit temporal buffering scheme for conditional residual video coding. Recent conditional coding methods propagate implicit temporal information for inter-frame coding, demonstrating superior coding…

图像与视频处理 · 电气工程与系统科学 2025-08-05 Yi-Hsin Chen , Kuan-Wei Ho , Martin Benjak , Jörn Ostermann , Wen-Hsiao Peng