we propose PAM, a novel sequence memory architecture with desirable generative properties. PAM is a streaming model that learns a sequence in an online, continuous manner by observing each input only once. Additionally, we find that PAM avoids catastrophic forgetting by uniquely representing past context through lateral inhibition in cortical minicolumns, which prevents new memories from overwriting previously learned knowledge. PAM generates future predictions by sampling from a union set of predicted possibilities; this generative ability is realized through an attractor model trained alongside the predictor. We show that PAM is trained with local computations through Hebbian plasticity rules in a biologically plausible framework. Other desirable traits (e.g., noise tolerance, CPU-based learning, capacity scaling) are discussed throughout the paper.

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. Notably, our model is fully self-supervised and trained in a streaming manner, enabling a single pass on the training 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.

The work highlights the importance of monitoring wildlife for conservation and conflict management. It highlights the success of AI-based camera traps in planning conservation efforts. This project, part of the NSF-TIH Indo-US partnership, aims to analyze longer bird videos, addressing challenges in video analysis at feeding and nesting sites. The goal is to create datasets and tools for automated video analysis to understand bird behavior. A major achievement is a dataset of high-quality images of Demoiselle cranes, revealing issues with current methods in tasks like segmentation and detection. The ongoing project aims to expand the dataset and develop better video analytics for wildlife monitoring.

Advances in visual perceptual tasks have been mainly driven by the amount, and types, of annotations of large scale datasets. Inspired by cognitive theories, we present a self-supervised perceptual prediction framework to tackle the problem of temporal event segmentation. Our approach is trained in an online manner on streaming input and requires only a single pass through the video, with no separate training set. Given the lack of long and realistic (includes real-world challenges) datasets, we introduce a new wildlife video dataset – nest monitoring of the Kagu (a flightless bird from New Caledonia) – to benchmark our approach. Our dataset features a video from 10 days (over 23 million frames) of continuous monitoring of the Kagu in its natural habitat. We annotate every frame with bounding boxes and event labels. Additionally, each frame is annotated with time-of-day and illumination conditions.

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.

We present a self-supervised perceptual prediction framework capable of temporal event segmentation by building stable representations of objects over time and demonstrate it on long videos, spanning several days. The self-learned attention maps effectively localize and track the event-related objects in each frame. The proposed approach does not require labels. It requires only a single pass through the video, with no separate training set.