Related papers: ECCO: Leveraging Cross-Camera Correlations for Eff…
Video enhancement is a challenging problem, more than that of stills, mainly due to high computational cost, larger data volumes and the difficulty of achieving consistency in the spatio-temporal domain. In practice, these challenges are…
With the development of artificial intelligence (AI) techniques and the increasing popularity of camera-equipped devices, many edge video analytics applications are emerging, calling for the deployment of computation-intensive AI models at…
Deep Learning Training (DLT) is a growing workload in shared GPU/CPU clusters due to its high computational cost and increasing number of jobs. This contributes to significant energy consumption in GPU clusters, further exacerbated by GPU…
While large deep neural networks excel at general video analytics tasks, the significant demand on computing capacity makes them infeasible for real-time inference on resource-constrained end cam-eras. In this paper, we propose an…
Domain-specific large language models (LLMs), typically developed by fine-tuning a pre-trained general-purpose LLM on specialized datasets, represent a significant advancement in applied AI. A common strategy in LLM fine-tuning is…
Applying image processing algorithms independently to each frame of a video often leads to undesired inconsistent results over time. Developing temporally consistent video-based extensions, however, requires domain knowledge for individual…
Deep neural networks are likely to fail when the test data is corrupted in real-world deployment (e.g., blur, weather, etc.). Test-time optimization is an effective way that adapts models to generalize to corrupted data during testing,…
The In-context generation paradigm recently has demonstrated strong power in instructional image editing with both data efficiency and synthesis quality. Nevertheless, shaping such in-context learning for instruction-based video editing is…
Researchers have presented systems for efficiently analysing video data at scale using sampling algorithms. While these systems effectively leverage the temporal redundancy present in videos, they suffer from three limitations. First, they…
The challenge in LLM-based video understanding lies in preserving visual and semantic information in long videos while maintaining a memory-affordable token count. However, redundancy and correspondence in videos have hindered the…
While large scale pre-training has achieved great achievements in bridging the gap between vision and language, it still faces several challenges. First, the cost for pre-training is expensive. Second, there is no efficient way to handle…
The conventional training approach for image captioning involves pre-training a network using teacher forcing and subsequent fine-tuning with Self-Critical Sequence Training to maximize hand-crafted captioning metrics. However, when…
Continual learning aims to enable models to adapt to new datasets without losing performance on previously learned data, often assuming that prior data is no longer available. However, in many practical scenarios, both old and new data are…
In IoT based distributed network of cameras, real-time multi-camera video analytics is challenged by high bandwidth demands and redundant visual data, creating a fundamental tension where reducing data saves network overhead but can degrade…
Recent advancements in large-scale pre-training of visual-language models on paired image-text data have demonstrated impressive generalization capabilities for zero-shot tasks. Building on this success, efforts have been made to adapt…
A new unified video analytics framework (ER3) is proposed for complex event retrieval, recognition and recounting, based on the proposed video imprint representation, which exploits temporal correlations among image features across video…
Continual learning has emerged as a crucial paradigm for learning from sequential data while preserving previous knowledge. In the realm of continual graph learning, where graphs continuously evolve based on streaming graph data, continual…
Edge computing is being widely used for video analytics. To alleviate the inherent tension between accuracy and cost, various video analytics pipelines have been proposed to optimize the usage of GPU on edge nodes. Nonetheless, we find that…
Recent developments and emerging use cases, such as smart Internet of Things (IoT) and Edge AI, have sparked considerable interest in the training of neural networks over fully decentralized (serverless) networks. One of the major…
Driven by advances in computer vision and the falling costs of camera hardware, organizations are deploying video cameras en masse for the spatial monitoring of their physical premises. Scaling video analytics to massive camera deployments,…