Related papers: ReSpec: Relevance and Specificity Grounded Online …

Deep networks allow to obtain outstanding results in semantic segmentation, however they need to be trained in a single shot with a large amount of data. Continual learning settings where new classes are learned in incremental steps and…

To improve the efficiency and sustainability of learning deep models, we propose CREST, the first scalable framework with rigorous theoretical guarantees to identify the most valuable examples for training non-convex models, particularly…

Selecting informative frames from long videos is a combinatorial problem that existing methods address either through efficient heuristics without explicit modeling of query-conditioned temporal structure, or through multi stage retrieval…

We propose a method for learning from streaming visual data using a compact, constant size representation of all the data that was seen until a given moment. Specifically, we construct a 'coreset' representation of streaming data using a…

Stream Learning (SL) requires models that can quickly adapt to continuously evolving data, posing significant challenges in both computational efficiency and learning accuracy. Effective data selection is critical in SL to ensure a balance…

Thispaperaimstoresearchandimplementa real-timevideotargettrackingalgorithmbasedon ConvolutionalNeuralNetworks(CNN),enhancingthe accuracyandrobustnessoftargettrackingincomplex scenarios.Addressingthelimitationsoftraditionaltracking…

Word embeddings have become essential components in various information retrieval and natural language processing tasks, such as ranking, document classification, and question answering. However, despite their widespread use, traditional…

In recent years, deep learning based visual tracking methods have obtained great success owing to the powerful feature representation ability of Convolutional Neural Networks (CNNs). Among these methods, classification-based tracking…

Video streaming analytics is a crucial workload for vision-language model serving, but the high cost of multimodal inference limits scalability. Prior systems reduce inference cost by exploiting temporal and spatial redundancy in video…

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…

We propose a framework to perform streaming covariance selection. Our approach employs regularization constraints where a time-varying sparsity parameter is iteratively estimated via stochastic gradient descent. This allows for the…

Online imitation learning is the problem of how best to mimic expert demonstrations, given access to the environment or an accurate simulator. Prior work has shown that in the infinite sample regime, exact moment matching achieves value…

Recent progress in Large Multi-modal Models (LMMs) has enabled effective vision-language reasoning, yet the ability to understand video content remains constrained by suboptimal frame selection strategies. Existing approaches often rely on…

Vision-Language Models (VLMs) have demonstrated strong performance on tasks such as video captioning and visual question answering. However, their growing scale and video-level inputs lead to significant computational and memory overhead,…

Reading text from images remains challenging due to multi-orientation, perspective distortion and especially the curved nature of irregular text. Most of existing approaches attempt to solve the problem in two or multiple stages, which is…

Single-image super-resolution refers to the reconstruction of a high-resolution image from a single low-resolution observation. Although recent deep learning-based methods have demonstrated notable success on simulated datasets -- with…

Real-time video analytics systems typically deploy lightweight models on edge devices to reduce latency. However, the distribution of data features may change over time due to various factors such as changing lighting and weather…

Streaming rendered content is an attractive way to bring high-quality graphics to billions of mobile devices that do not have sufficient rendering power. Existing solutions render content on a server at a fixed frame rate, typically 30 or…

Video-text retrieval (VTR) aims to locate relevant videos using natural language queries. Current methods, often based on pre-trained models like CLIP, are hindered by video's inherent redundancy and their reliance on coarse, final-layer…

Reinforcement learning (RL) plays a central role in improving the reasoning and alignment of large language models, yet its efficiency critically depends on how training data are selected. Existing online selection strategies predominantly…