相关论文: Leveraging Bitstream Metadata for Fast, Accurate, …

Experience and reasoning occur across multiple temporal scales: milliseconds, seconds, hours or days. The vast majority of computer vision research, however, still focuses on individual images or short videos lasting only a few seconds.…

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

Learned image compression sits at the intersection of machine learning and image processing. With advances in deep learning, neural network-based compression methods have emerged. In this process, an encoder maps the image to a…

Recent works have shown that learned models can achieve significant performance gains, especially in terms of perceptual quality measures, over traditional methods. Hence, the state of the art in image restoration and compression is getting…

Video compression is a critical component of Internet video delivery. Recent work has shown that deep learning techniques can rival or outperform human-designed algorithms, but these methods are significantly less compute and…

Video tokenizers are essential for latent video diffusion models, converting raw video data into spatiotemporally compressed latent spaces for efficient training. However, extending state-of-the-art video tokenizers to achieve a temporal…

Nowadays, real-time video communication over the internet through video conferencing applications has become an invaluable tool in everyone's professional and personal life. This trend underlines the need for video coding algorithms that…

Video analytics are often performed as cloud services in edge settings, mainly to offload computation, and also in situations where the results are not directly consumed at the video sensors. Sending high-quality video data from the edge…

Encryption on the internet with the shift to HTTPS has been an important step to improve the privacy of internet users. However, there is an increasing body of work about extracting information from encrypted internet traffic without having…

To exploit high temporal correlations in video frames of the same scene, the current frame is predicted from the already-encoded reference frames using block-based motion estimation and compensation techniques. While this approach can…

Conventional video compression approaches use the predictive coding architecture and encode the corresponding motion information and residual information. In this paper, taking advantage of both classical architecture in the conventional…

Over the last decade, deep learning has shown great success at performing computer vision tasks, including classification, super-resolution, and style transfer. Now, we apply it to data compression to help build the next generation of…

Dataset distillation has demonstrated remarkable effectiveness in high-compression scenarios for image datasets. While video datasets inherently contain greater redundancy, existing video dataset distillation methods primarily focus on…

While recent machine learning research has revealed connections between deep generative models such as VAEs and rate-distortion losses used in learned compression, most of this work has focused on images. In a similar spirit, we view…

The scalability of video understanding models is increasingly limited by the prohibitive storage and computational costs of large-scale video datasets. While data synthesis has improved data efficiency in the image domain, its extension to…

Learned image compression methods generally optimize a rate-distortion loss, trading off improvements in visual distortion for added bitrate. Increasingly, however, compressed imagery is used as an input to deep learning networks for…

Existing video captioning approaches typically require to first sample video frames from a decoded video and then conduct a subsequent process (e.g., feature extraction and/or captioning model learning). In this pipeline, manual frame…

While learning based compression techniques for images have outperformed traditional methods, they have not been widely adopted in machine learning pipelines. This is largely due to lack of standardization and lack of retention of salient…

Bitstream-corrupted video recovery aims to restore realistic content degraded during video storage or transmission. Existing methods typically assume that predefined masks of corrupted regions are available, but manually annotating these…

Training robust deep video representations has proven to be much more challenging than learning deep image representations. This is in part due to the enormous size of raw video streams and the high temporal redundancy; the true and…