Surveillance systems such as bodycams and drones often operate under bandwidth constraints that limit video quality and degrade both human monitoring and AI-based analytics. Traditional compression techniques introduce artifacts that obscure critical details, especially in high-motion scenarios. We present a generative AI-powered video compression framework developed by Small Pixels, a spin-off of the University of Florence, designed to deliver Full HD video at significantly reduced bitrates. The system combines edge-side preprocessing for compression resilience with real-time receiver-side super-resolution, enabling up to 50% bandwidth savings while preserving perceptual quality and detection accuracy. Objective evaluations on EgoSeg and VisDrone datasets show +6.2 VMAF improvement and stable YOLOv11 detection performance with 30% less bitrate. Live trials in Singapore, within the Singapore Hatch-X Global Innovation Program, validated real-time operation with minimal latency, demonstrating clearer faces and motion in challenging conditions. The solution integrates seamlessly into existing infrastructures without hardware upgrades, offering a practical path to reliable, high-quality video streaming in bandwidth-limited environments.

Compatible features enable the direct comparison of old and new learned features allowing to use them interchangeably over time. In visual search systems, this eliminates the need to extract new features from the gallery-set when the representation model is upgraded with novel data. This has a big value in real applications as re-indexing the gallery-set can be computationally expensive when the gallery-set is large, or even infeasible due to privacy or other concerns of the application. In this paper, we propose CoReS, a new training procedure to learn representations that are compatible with those previously learned, grounding on the stationarity of the features as provided by fixed classifiers based on polytopes. With this solution, classes are maximally separated in the representation space and maintain their spatial configuration stationary as new classes are added, so that there is no need to learn any mappings between representations nor to impose pairwise training with the previously learned model. We demonstrate that our training procedure largely outperforms the current state of the art and is particularly effective in the case of multiple upgrades of the training-set, which is the typical case in real applications.

Neural networks are widely used as a model for classification in a large variety of tasks. Typically, a learnable transformation (i.e., the classifier) is placed at the end of such models returning a value for each class used for classification. This transformation plays an important role in determining how the generated features change during the learning process. In this work, we argue that this transformation not only can be fixed (i.e., set as nontrainable) with no loss of accuracy and with a reduction in memory usage, but it can also be used to learn stationary and maximally separated embeddings. We show that the stationarity of the embedding and its maximal separated representation can be theoretically justified by setting the weights of the fixed classifier to values taken from the coordinate vertices of the three regular polytopes available in [Formula: see text], namely, the d -Simplex, the d -Cube, and the d -Orthoplex. These regular polytopes have the maximal amount of symmetry that can be exploited to generate stationary features angularly centered around their corresponding fixed weights. Our approach improves and broadens the concept of a fixed classifier, recently proposed by Hoffer et al., to a larger class of fixed classifier models. Experimental results confirm the theoretical analysis, the generalization capability, the faster convergence, and the improved performance of the proposed method. Code will be publicly available.

In this article, we propose a method to partially mimic natural intelligence for the problem of lifelong learning representations that are compatible. We take the perspective of a learning agent that is interested in recognizing object instances in an open dynamic universe in a way in which any update to its internal feature representation does not render the features in the gallery unusable for visual search. We refer to this learning problem as Compatible Lifelong Learning Representations (CL 2 R), as it considers compatible representation learning within the lifelong learning paradigm. We identify stationarity as the property that the feature representation is required to hold to achieve compatibility and propose a novel training procedure that encourages local and global stationarity on the learned representation. Due to stationarity, the statistical properties of the learned features do not change over time, making them interoperable with previously learned features. Extensive experiments on standard benchmark datasets show that our CL 2 R training procedure outperforms alternative baselines and state-of-the-art methods. We also provide novel metrics to specifically evaluate compatible representation learning under catastrophic forgetting in various sequential learning tasks. Code is available at https://github.com/NiccoBiondi/CompatibleLifelongRepresentation .

In class-incremental learning, a learning agent faces a stream of data with the goal of learning new classes while not forgetting previous ones. Neural networks are known to suffer under this setting, as they forget previously acquired knowledge. To address this problem, effective methods exploit past data stored in an episodic memory while expanding the final classifier nodes to accommodate the new classes. In this work, we substitute the expanding classifier with a novel fixed classifier in which a number of pre-allocated output nodes are subject to the classification loss right from the beginning of the learning phase. Contrarily to the standard expanding classifier, this allows: (a) the output nodes of future unseen classes to firstly see negative samples since the beginning of learning together with the positive samples that incrementally arrive; (b) to learn features that do not change their geometric configuration as novel classes are incorporated in the learning model. Experiments with public datasets show that the proposed approach is as effective as the expanding classifier while exhibiting novel intriguing properties of the internal feature representation that are otherwise not-existent. Our ablation study on pre-allocating a large number of classes further validates the approach.

We present a novel online unsupervised method for face identity learning from video streams. The method exploits deep face descriptors together with a memory based learning mechanism that takes advantage of the temporal coherence of visual data. Specifically, we introduce a discriminative descriptor matching solution based on Reverse Nearest Neighbour and a forgetting strategy that detect redundant descriptors and discard them appropriately while time progresses. It is shown that the proposed learning procedure is asymptotically stable and can be effectively used in relevant applications like multiple face identification and tracking from unconstrained video streams. Experimental results show that the proposed method achieves comparable results in the task of multiple face tracking and better performance in face identification with offline approaches exploiting future information. Code will be publicly available.

We present a novel method to improve action recognition by leveraging a set of captioned videos. By learning linear projections to map videos and text onto a common space, our approach shows that improved results on unseen videos can be obtained. We also propose a novel structure preserving loss that further ameliorates the quality of the projections. We tested our method on the challenging, realistic, Hollywood2 action recognition dataset where a considerable gain in performance is obtained. We show that the gain is proportional to the number of training samples used to learn the projections.