Related papers: Task-Aware Encoder Control for Deep Video Compress…
Content-adaptive compression has always been a key direction in neural video coding (NVC), aiming to mitigate the domain gap between training and testing data. Such gaps often arise from distributional discrepancies between training and…
Autonomous driving systems require a comprehensive understanding of the environment, achieved by extracting visual features essential for perception, planning, and control. However, models trained solely on single-task objectives or generic…
Recently, Neural Video Compression (NVC) techniques have achieved remarkable performance, even surpassing the best traditional lossy video codec. However, most existing NVC methods heavily rely on transmitting Motion Vector (MV) to generate…
Large Vision-Language Models (VLMs) have been extended to understand both images and videos. Visual token compression is leveraged to reduce the considerable token length of visual inputs. To meet the needs of different tasks, existing…
Image compression is a widely used technique to reduce the spatial redundancy in images. Recently, learning based image compression has achieved significant progress by using the powerful representation ability from neural networks.…
Despite a short history, neural image codecs have been shown to surpass classical image codecs in terms of rate-distortion performance. However, most of them suffer from significantly longer decoding times, which hinders the practical…
We aim to train a multi-task model such that users can adjust the desired compute budget and relative importance of task performances after deployment, without retraining. This enables optimizing performance for dynamically varying user…
Humans do not understand individual events in isolation; rather, they generalize concepts within classes and compare them to others. Existing audio-video pre-training paradigms only focus on the alignment of the overall audio-video…
Recent advancements in large video-language models have revolutionized video understanding tasks. However, their efficiency is significantly constrained by processing high volumes of visual tokens. Existing token compression strategies…
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,…
We present a deep learning method for composite and task-driven motion control for physically simulated characters. In contrast to existing data-driven approaches using reinforcement learning that imitate full-body motions, we learn…
The proliferation of high resolution videos posts great storage and bandwidth pressure on cloud video services, driving the development of next-generation video codecs. Despite great progress made in neural video coding, existing approaches…
Tokenized visual representations have shown promise in image compression, yet their extension to video remains underexplored due to the challenges posed by complex temporal dynamics and stringent bit rate constraints. In this paper, we…
Building correspondences across different modalities, such as video and language, has recently become critical in many visual recognition applications, such as video captioning. Inspired by machine translation, recent models tackle this…
In recent years, end-to-end learnt video codecs have demonstrated their potential to compete with conventional coding algorithms in term of compression efficiency. However, most learning-based video compression models are associated with…
Although deep convolutional neural network has been proved to efficiently eliminate coding artifacts caused by the coarse quantization of traditional codec, it's difficult to train any neural network in front of the encoder for gradient's…
One of the major differentiators unlocked by learned codecs relative to their hard-coded traditional counterparts is their ability to be optimized directly to appeal to the human visual system. Despite this potential, a perceptual yet…
The integration of advanced video codecs into the streaming pipeline is growing in response to the increasing demand for high quality video content. However, the significant computational demand for advanced codecs like Versatile Video…
World models based on video generation demonstrate remarkable potential for simulating interactive environments but face persistent difficulties in two key areas: maintaining long-term content consistency when scenes are revisited and…
In this paper, a hybrid video compression framework is proposed that serves as a demonstrative showcase of deep learning-based approaches extending beyond the confines of traditional coding methodologies. The proposed hybrid framework is…