Melika Ayoughi

Email  /  CV  /  LinkedIn  /  Twitter  /  Github

I am a PhD student at the University of Amsterdam, where I work on extracting knowledge graphs from videos. I'm supervised jointly by Pascal Mettes from VIS Lab and Paul Groth from INDE Lab.

During my internship at Apple MLR, I worked with Hanlin on self-supervised pertaining of transformers using relative patch transformations. Before my PhD, I did an Artificial Intelligence master at the University of Amsterdam. I worked on my thesis at TomTom on object detection under high class imbalance. I took part in an internship at Dexter Energy Services working on weather nowcasting using satellite images.

I'm interested in computer vision, and specifically multimodal data such as video, audio, text and graph. I would like to work on improving high-level understanding of videos such as object-centric learning and relationship detection and easing retrieval by storing information in a knowledge graph. I'm currenlty working on a project to learn better instance-level represetations using prior knowledge.

Self-Contained Entity Discovery from Captioned Videos

This paper introduces the task of visual named entity discovery in videos without the need for task-specific supervision or task-specific external knowledge sources. Assigning specific names to entities (e.g. faces, scenes, or objects) in video frames is a long-standing challenge. Commonly, this problem is addressed as a supervised learning objective by manually annotating faces with entity labels. To bypass the annotation burden of this setup, several works have investigated the problem by utilizing external knowledge sources such as movie databases. While effective, such approaches do not work when task-specific knowledge sources are not provided and can only be applied to movies and TV series. In this work, we take the problem a step further and propose to discover entities in videos from videos and corresponding captions or subtitles. We introduce a three-stage method where we (i) create bipartite entity-name graphs from frame-caption pairs, (ii) find visual entity agreements, and (iii) refine the entity assignment through entity-level prototype construction. To tackle this new problem, we outline two new benchmarks SC-Friends and SC-BBT based on the Friends and Big Bang Theory TV series. Experiments on the benchmarks demonstrate the ability of our approach to discover which named entity belongs to which face or scene, with an accuracy close to a supervised oracle, just from the multimodal information present in videos. Additionally, our qualitative examples show the potential challenges of self-contained discovery of any visual entity for future work.

PART: Self-supervised Pretraining with Pairwise Relative Translations

Images are often composed of objects and object parts that are related to each other but are not necessarily related to their absolute position in the image frame. For instance, the pose of a person's nose is consistent relative to the forehead, while that same nose can be anywhere in absolute position in the image frame. To capture these underlying relative relationships, we introduce PART, a novel pretraining approach that predicts pairwise relative translations between randomly sampled input patches. Through this process, the original patch positions are masked out. The pretraining objective is to predict the pairwise translation parameters for any set of patches, just using the patch content. Our object detection experiments on COCO show improved performance over strong baselines such as MAE and DropPos. Our method is competitive on the ImageNet-1k classification benchmark. Beyond vision, we also outperform baselines on 1D time series prediction tasks. The code and models will be available soon.

Continual Hyperbolic Learning of Instances and Classes

Instance-level continual learning addresses the challenging problem of recognizing and remembering specific instances of object classes in an incremental setup, where new instances appear over time. Continual learning of instances forms a more fine-grained challenge than conventional continual learning, which is only concerned with incremental discrimination at the class-level. In this paper, we argue that for real-world continual understanding, we need to recognize samples both at the instance- and class-level. We find that classes and instances form a hierarchical structure. To enable us to learn from this structure, we propose a hyperbolic continual learning algorithm for visual instances and classes. We introduce continual hyperbolic classification and distillation, allowing us to embed the hierarchical relations between classes and from classes to instances. Empirical evaluations show that our method can operate effectively at both levels of granularity and with better hierarchical generalization, outperforming well-known continual learning algorithms.