Search for: All records

We present a novel self-supervised approach for hierarchical representation learning and segmentation of perceptual inputs in a streaming fashion. Our research addresses how to semantically group streaming inputs into chunks at various levels of a hierarchy while simultaneously learning, for each chunk, robust global representations throughout the domain. To achieve this, we propose STREAMER, an architecture that is trained layer-by-layer, adapting to the complexity of the input domain. In our approach, each layer is trained with two primary objectives: making accurate predictions into the future and providing necessary information to other levels for achieving the same objective. The event hierarchy is constructed by detecting prediction error peaks at different levels, where a detected boundary triggers a bottom-up information flow. At an event boundary, the encoded representation of inputs at one layer becomes the input to a higher-level layer. Additionally, we design a communication module that facilitates top-down and bottom-up exchange of information during the prediction process. Notably, our model is fully self-supervised and trained in a streaming manner, enabling a single pass on the training data. This means that the model encounters each input only once and does not store the data. We evaluate the performance of our model on the egocentric EPIC-KITCHENS dataset, specifically focusing on temporal event segmentation. Furthermore, we conduct event retrieval experiments using the learned representations to demonstrate the high quality of our video event representations. Illustration videos and code are available on our project page: https://ramymounir.com/publications/streamer 

Event perception tasks such as recognizing and localizing actions in streaming videos are essential for scaling to real-world application contexts. We tackle the problem of learning actor-centered representations through the notion of continual hierarchical predictive learning to localize actions in streaming videos without the need for training labels and outlines for the objects in the video. We propose a framework driven by the notion of hierarchical predictive learning to construct actor-centered features by attention-based contextualization. The key idea is that predictable features or objects do not attract attention and hence do not contribute to the action of interest. Experiments on three benchmark datasets show that the approach can learn robust representations for localizing actions using only one epoch of training, i.e., a single pass through the streaming video. We show that the proposed approach outperforms unsupervised and weakly supervised baselines while offering competitive performance to fully supervised approaches. Additionally, we extend the model to multi-actor settings to recognize group activities while localizing the multiple, plausible actors. We also show that it generalizes to out-of-domain data with limited performance degradation. 

This search for magnetic monopoles (MMs) and high electric charge objects (HECOs) with spins 0, $1/2$, and 1, uses for the first time the full MoEDAL detector, exposed to $6.46{\mathrm{fb}}^{-1}$proton-proton collisions at 13 TeV. The results are interpreted in terms of Drell-Yan and photon-fusion pair production. Mass limits on direct production of MMs of up to 10 Dirac magnetic charges and HECOs with electric charge in the range $10e$to $400e$, were achieved. The charge limits placed on MM and HECO production are currently the strongest in the world. MoEDAL is the only LHC experiment capable of being directly calibrated for highly ionizing particles using heavy ions and with a detector system dedicated to definitively measuring magnetic charge. Published by the American Physical Society2025 

Graph-based representations are becoming increasingly popular for representing and analyzing video data, especially in object tracking and scene understanding applications. Accordingly, an essential tool in this approach is to generate statistical inferences for graphical time series associated with videos. This paper develops a Kalman-smoothing method for estimating graphs from noisy, cluttered, and incomplete data. The main challenge here is to find and preserve the registration of nodes (salient detected objects) across time frames when the data has noise and clutter due to false and missing nodes. First, we introduce a quotient-space representation of graphs that incorporates temporal registration of nodes, and we use that metric structure to impose a dynamical model on graph evolution. Then, we derive a Kalman smoother, adapted to the quotient space geometry, to estimate dense, smooth trajectories of graphs. We demonstrate this framework using simulated data and actual video graphs extracted from the Multiview Extended Video with Activities (MEVA) dataset. This framework successfully estimates graphs despite the noise, clutter, and missed detections. 

We report on a search for magnetic monopoles (MMs) produced in ultraperipheral Pb-Pb collisions during Run 1 of the LHC. The beam pipe surrounding the interaction region of the CMS experiment was exposed to $184.07\mathrm{\mu }{\mathrm{b}}^{-1}$of Pb-Pb collisions at 2.76 TeV center-of-mass energy per collision in December 2011, before being removed in 2013. It was scanned by the MoEDAL experiment using a SQUID magnetometer to search for trapped MMs. No MM signal was observed. The two distinctive features of this search are the use of a trapping volume very close to the collision point and ultrahigh magnetic fields generated during the heavy-ion run that could produce MMs via the Schwinger effect. These two advantages allowed setting the first reliable, world-leading mass limits on MMs with high magnetic charge. In particular, the established limits are the strongest available in the range between 2 and 45 Dirac units, excluding MMs with masses of up to 80 GeV at a 95% confidence level. Published by the American Physical Society2024 

Complex analyses involving multiple, dependent random quantities often lead to graphical models—a set of nodes denoting variables of interest, and corresponding edges denoting statistical interactions between nodes. To develop statistical analyses for graphical data, especially towards generative modeling, one needs mathematical representations and metrics for matching and comparing graphs, and subsequent tools, such as geodesics, means, and covariances. This paper utilizes a quotient structure to develop efficient algorithms for computing these quantities, leading to useful statistical tools, including principal component analysis, statistical testing, and modeling. We demonstrate the efficacy of this framework using datasets taken from several problem areas, including letters, biochemical structures, and social networks.