Related papers: Low-Latency Neural Stereo Streaming
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…
Recent feed-forward reconstruction models like VGGT and $\pi^3$ achieve impressive reconstruction quality but cannot process streaming videos due to quadratic memory complexity, limiting their practical deployment. While existing streaming…
Tensor-based multi-view clustering has recently received significant attention due to its exceptional ability to explore cross-view high-order correlations. However, most existing methods still encounter some limitations. (1) Most of them…
End-to-end (E2E) delay is critical for interactive video streaming (IVS) experiences, but remains unsatisfactory for its long-tail distribution caused by periodic large keyframes. Conventional optimization strategies, such as jitter buffer,…
Finding accurate correspondences among different views is the Achilles' heel of unsupervised Multi-View Stereo (MVS). Existing methods are built upon the assumption that corresponding pixels share similar photometric features. However,…
Error-bounded lossy compression is one of the most efficient solutions to reduce the volume of scientific data. For lossy compression, progressive decompression and random-access decompression are critical features that enable on-demand…
This paper studies secure video streaming in cache-enabled small cell networks, where some of the cache-enabled small cell base stations (BSs) helping in video delivery are untrusted. Unfavorably, caching improves the eavesdropping…
Recent advances in deep learning have markedly improved the quality of visual-attention modelling. In this work we apply these advances to video compression. We propose a compression method that uses a saliency model to adaptively compress…
Existing tracking algorithms typically rely on low-frame-rate RGB cameras coupled with computationally intensive deep neural network architectures to achieve effective tracking. However, such frame-based methods inherently face challenges…
Feedforward models for novel view synthesis (NVS) have recently advanced by transformer-based methods like LVSM, using attention among all input and target views. In this work, we argue that its full self-attention design is suboptimal,…
Human vision is dynamic and continuous. However, in video understanding with multimodal large language models (LLMs), existing methods primarily rely on static features extracted from images sampled at a fixed low frame rate of…
Neural transducers provide a natural way of streaming ASR. However, they augment output sequences with blank tokens which leads to challenges for domain adaptation using text data. This paper proposes a label-synchronous neural transducer…
Despite the recent developments in the field of cross-modal retrieval, there has been less research focusing on low-resource languages due to the lack of manually annotated datasets. In this paper, we propose a noise-robust cross-lingual…
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,…
We consider three types of application layer coding for streaming over lossy links: random linear coding, systematic random linear coding, and structured coding. The file being streamed is divided into sub-blocks (generations). Code symbols…
Streaming video understanding requires models to robustly encode, store, and retrieve information from a continuous video stream to support accurate video question answering (VQA). Existing state-of-the-art approaches rely on key-value…
Recently, learned video compression (LVC) has shown superior performance under low-delay configuration. However, the performance of learned bi-directional video compression (LBVC) still lags behind traditional bi-directional coding. The…
4D Gaussian Splatting (4DGS) enables high-quality dynamic novel view synthesis, yet current models remain monolithic bitstreams that clients must download in full before any frame can be rendered, causing black-screen waits of tens to…
Semantic Segmentation is an important module for autonomous robots such as self-driving cars. The advantage of video segmentation approaches compared to single image segmentation is that temporal image information is considered, and their…
Training-free video large language models (LLMs) leverage pretrained Image LLMs to process video content without the need for further training. A key challenge in such approaches is the difficulty of retaining essential visual and temporal…