With the widespread deployment of edge computing, the focus has shifted to machine-centric live video streaming, where endpoint-collected videos are transmitted over networks to edge servers for analysis. Unlike maximizing user's Quality of Experience (QoE), machine-centric video streaming optimizes the machine's Quality of Inference (QoI) by balancing the inference accuracy, inference delay, and transmission latency with video adaptive configuration. Traditional heuristic configuration adaption methods are reliable but unable to respond to erratic network fluctuations. Reinforcement learning (RL) based algorithms exhibit superior flexibility but suffer from exploration mechanisms, resulting in long-tail effects on upload latency. In this paper, we propose FHVAC, which dynamically selects video encoding parameters for live streaming by coherently fusing rule-based and RL-based agent at the feature level. We initially develop a robust rule-based approach for ensuring the low latency in transmission, and employ imitation learning to convert it into a neural network equivalently. Subsequently, we design a novel module to combine the two approaches and assess various fusion mechanisms. Our evaluation of FHVAC across two vision tasks (pose estimation and semantic segmentation) in two scenarios (trace-driven simulation and testbed-based experiment) shows that FHVAC enhances the average QoI, and reduces 10.61%-65.27% latency tail performance compared to prior work.

Currently, HTTP adaptive streaming (HAS) is the state-of-the-art technology for mobile video streaming. The rate adaptation of HAS has been designed to make a trade-off between two contrasting requirements, i.e., enhancing the quality of a video, and reducing the probability of video freezes, by adaptively switching between different video bitrates during a video playback session. This process becomes more challenging when moving onto an long term evolution (LTE) cellular network due to the unstable nature of the wireless channel. In this paper, we propose the bandwidth variation pattern-differentiated rate adaptation (BVPDRA) algorithm for LTE cellular networks. Unlike prior works, BVPDRA does not strike a balance between the stableness and responsiveness of bitrate switching in the case of bandwidth capacity variations. BVPDRA differentiates between bandwidth variation patterns of the LTE cellular network as either constant bandwidth fluctuations or instantaneous bandwidth hopping. Accordingly, BVPDRA operates with a dual character: for the constant bandwidth fluctuations, BVPDRA performs smoothed bandwidth prediction and conservative rate switching to minimize video quality version oscillations; for the instantaneous bandwidth hopping, BVPDRA performs positive bandwidth prediction and aggressive rate switching to maximize the bandwidth utilization and minimize the risk of playback stalling. We empirically evaluate the performance of BVPDRA on an LTE cellular network testbed. The results demonstrate that BVPDRA achieves a higher average bitrate, and lower rebuffering ratio with a reduced bitrate switching frequency.

HTTP adaptive streaming (HAS) technology has been increasingly employed by video service providers (VSPs) due to its prominent benefits such as reducing interruptions of video playback and achieving higher bandwidth utilization and outstanding quality of experience (QoE). Many VSPs have deployed HAS applications in the media cloud to provide large-scale on-demand or live video streaming services. At present, research into the media cloud typically focuses on the management and optimization of cloud resources, such as the placement and migration of virtual machines in media cloud data centers. However, considering the HAS live video streaming service, existing related works have not adequately discussed the specific impact of the consumption of computing and bandwidth resources of media cloud servers on the user experience (QoE), particularly under the resource constraints in the media cloud. In this paper, we first investigate and formulate the computing and bandwidth resource consumption characteristics of HAS live video streaming with different frame rates and resolutions and further establish a resources-aware QoE model to quantify the user experience of live video channels (i.e. programs). Then, based on the model, we present a QoE-driven HAS live video channel placement approach (including a placement algorithm HCP and a rescheduling algorithm HCR) to optimize the channel allocation in media cloud servers, aiming to maximize the average user QoE. The experimental results demonstrate the effectiveness of our proposed approach compared with benchmark solutions.

Continual learning for open-vocabulary object detection aims to enable pretrained vision–language detectors to adapt to diverse specialized domains while preserving their zero-shot generalization capabilities. However, existing methods primarily focus on mitigating catastrophic forgetting, often neglecting the substantial domain shifts commonly encountered in real-world applications. To address this critical oversight, we pioneer Open-Domain Continual Object Detection (OD-COD), a new paradigm that requires detectors to continually adapt across domains with significant stylistic gaps. We propose Disentangled Domain Knowledge-Aided Learning (D-Know) to tackle this challenge. This framework explicitly disentangles domain-general priors from category-specific adaptation, managing them dynamically in a scalable domain knowledge base. Specifically, D-Know first learns domain priors in a self-supervised manner and then leverages these priors to facilitate category-specific adaptation within each domain. To rigorously evaluate this task, we construct OD-CODB, the first dedicated benchmark spanning six domains with substantial visual variations. Extensive experiments demonstrate that D-Know achieves superior performance, surpassing current state-of-the-art methods by an average of 4.2% mAP under open-domain continual settings while maintaining strong zero-shot generalization. Furthermore, experiments under the few-shot setting confirm D-Know’s superior data efficiency.

Convolutional Neural Networks (CNNs) have achieved remarkable performance in computer vision tasks, but their deployment on resource-constrained devices remains challenging. While existing lightweight CNNs reduce FLOPs significantly, their practical inference speed is limited by memory access bottlenecks. We hence propose CFNet, an efficient architecture that bridges the gap between theoretical efficiency and practical speed through synergistic design of channel-focused convolution (CFConv) and channel mixed unit (CMU). CFConv dynamically selects informative channels via learnable GroupNorm scaling factors and reparameterization, reducing both FLOPs and memory access, while CMU enables cross-channel communication through a split-transform-and-mix strategy to mitigate information loss. Experiments on CIFAR/ImageNet classification and MS COCO object detection demonstrate CFNet’s superior performance. On ImageNet-1K, CFNet-A achieves 35.5% and 189.4% GPU throughput improvements over MobileNetV2 and MobileViTv1-XXS respectively, while delivering 1.76% and 4.09% accuracy gains. CFNet-E attains 83.5% top-1 accuracy, outperforming Swin-S by 0.47% with 44.6% higher GPU throughput and 43.6% lower CPU inference latency.