Related papers: Veritas: Answering Causal Queries from Video Strea…
Multimodal large language models (MLLMs) have shown strong performance on offline video understanding, but most are limited to offline inference or have weak online reasoning, making multi-turn interaction over continuously arriving video…
We introduce ViDaS, a two-stream, fully convolutional Video, Depth-Aware Saliency network to address the problem of attention modeling ``in-the-wild", via saliency prediction in videos. Contrary to existing visual saliency approaches using…
Online Video Large Language Models (VideoLLMs) play a critical role in supporting responsive, real-time interaction. Existing methods focus on streaming perception, lacking a synchronized logical reasoning stream. However, directly applying…
Vision-language-action (VLA) models have demonstrated exceptional performance in natural language-driven perception and control. However, the high computational cost of VLA models poses significant efficiency challenges, particularly for…
Virtual reality has been gaining popularity in recent years caused by the proliferation of affordable consumer-grade devices such as Oculus Rift, HTC Vive, and Samsung VR. Amongst the various VR applications, 360{\deg} video streaming is…
We formulate the problem of online temporal action detection in live streaming videos, acknowledging one important property of live streaming videos that there is normally a broadcast delay between the latest captured frame and the actual…
Transfer learning seeks to accelerate sequential decision-making by leveraging offline data from related agents. However, data from heterogeneous sources that differ in observed features, distributions, or unobserved confounders often…
Binaural rendering aims to synthesize binaural audio that mimics natural hearing based on a mono audio and the locations of the speaker and listener. Although many methods have been proposed to solve this problem, they struggle with…
Detecting memory corruption vulnerabilities in stripped binaries requires recovering object semantics, interprocedural propagation, and feasible triggers from low-level, lossy representations. Recent LLM-based approaches improve code…
With exponential increase in the availability oftelemetry / streaming / real-time data, understanding contextualbehavior changes is a vital functionality in order to deliverunrivalled customer experience and build high performance andhigh…
Video Anomaly Detection (VAD) identifies unusual activities in video streams, a key technology with broad applications ranging from surveillance to healthcare. Tackling VAD in real-life settings poses significant challenges due to the…
Recent work suggests that TCP throughput stability and predictability within a video viewing session can inform the design of better video bitrate adaptation algorithms. Despite a rich tradition of Internet measurement, however, our…
Causal discovery is at the core of human cognition. It enables us to reason about the environment and make counterfactual predictions about unseen scenarios that can vastly differ from our previous experiences. We consider the task of…
Multimodal LLMs are turning their focus to video benchmarks, however most video benchmarks only provide outcome supervision, with no intermediate or interpretable reasoning steps. This makes it challenging to assess if models are truly able…
Media streaming has been adopted for a variety of applications such as entertainment, visualization, and design. Unlike video/audio streaming where the content is usually consumed sequentially, 3D applications such as gaming require…
Dynamic adaptive streaming over HTTP (DASH) has recently been widely deployed in the Internet and adopted in the industry. It, however, does not impose any adaptation logic for selecting the quality of video fragments requested by clients…
With the rapid advancement of text-conditioned Video Generation Models (VGMs), the quality of generated videos has significantly improved, bringing these models closer to functioning as ``*world simulators*'' and making real-world-level…
Streaming Continual Learning (CL) typically converts a continuous stream into a sequence of discrete tasks through temporal partitioning. We argue that this temporal taskification step is not a neutral preprocessing choice, but a structural…
Reasoning about temporal causality, particularly irreversible transformations of objects governed by real-world knowledge (e.g., fruit decay and human aging), is a fundamental aspect of human visual understanding. Unlike temporal perception…
Diffusion models have revolutionized high-fidelity image and video synthesis, yet their computational demands remain prohibitive for real-time applications. These models face two fundamental challenges: strict temporal dependencies…