Bulat Khaertdinov

Bulat Khaertdinov, Stylianos Asteriadis

Automated Human Activity Recognition has long been a problem of great interest in human-centered and ubiquitous computing. In the last years, a plethora of supervised learning algorithms based on deep neural networks has been suggested to address this problem using various modalities. While every modality has its own limitations, there is one common challenge. Namely, supervised learning requires vast amounts of annotated data which is practically hard to collect. In this paper, we benefit from the self-supervised learning paradigm (SSL) that is typically used to learn deep feature representations from unlabeled data. Moreover, we upgrade a contrastive SSL framework, namely SimCLR, widely used in various applications by introducing a temporal feature alignment procedure for Human Activity Recognition. Specifically, we propose integrating a dynamic time warping (DTW) algorithm in a latent space to force features to be aligned in a temporal dimension. Extensive experiments have been conducted for the unimodal scenario with inertial modality as well as in multimodal settings using inertial and skeleton data. According to the obtained results, the proposed approach has a great potential in learning robust feature representations compared to the recent SSL baselines, and clearly outperforms supervised models in semi-supervised learning. The code for the unimodal case is available via the following link: https://github.com/bulatkh/csshar_tfa.

Razvan Brinzea, Bulat Khaertdinov, Stylianos Asteriadis

Human Activity Recognition is a field of research where input data can take many forms. Each of the possible input modalities describes human behaviour in a different way, and each has its own strengths and weaknesses. We explore the hypothesis that leveraging multiple modalities can lead to better recognition. Since manual annotation of input data is expensive and time-consuming, the emphasis is made on self-supervised methods which can learn useful feature representations without any ground truth labels. We extend a number of recent contrastive self-supervised approaches for the task of Human Activity Recognition, leveraging inertial and skeleton data. Furthermore, we propose a flexible, general-purpose framework for performing multimodal self-supervised learning, named Contrastive Multiview Coding with Cross-Modal Knowledge Mining (CMC-CMKM). This framework exploits modality-specific knowledge in order to mitigate the limitations of typical self-supervised frameworks. The extensive experiments on two widely-used datasets demonstrate that the suggested framework significantly outperforms contrastive unimodal and multimodal baselines on different scenarios, including fully-supervised fine-tuning, activity retrieval and semi-supervised learning. Furthermore, it shows performance competitive even compared to supervised methods.

Bulat Khaertdinov, Stylianos Asteriadis

In recent years, self-supervised learning (SSL) frameworks have been extensively applied to sensor-based Human Activity Recognition (HAR) in order to learn deep representations without data annotations. While SSL frameworks reach performance almost comparable to supervised models, studies on interpreting representations learnt by SSL models are limited. Nevertheless, modern explainability methods could help to unravel the differences between SSL and supervised representations: how they are being learnt, what properties of input data they preserve, and when SSL can be chosen over supervised training. In this paper, we aim to analyze deep representations of two recent SSL frameworks, namely SimCLR and VICReg. Specifically, the emphasis is made on (i) comparing the robustness of supervised and SSL models to corruptions in input data; (ii) explaining predictions of deep learning models using saliency maps and highlighting what input channels are mostly used for predicting various activities; (iii) exploring properties encoded in SSL and supervised representations using probing. Extensive experiments on two single-device datasets (MobiAct and UCI-HAR) have shown that self-supervised learning representations are significantly more robust to noise in unseen data compared to supervised models. In contrast, features learnt by the supervised approaches are more homogeneous across subjects and better encode the nature of activities.

Esam Ghaleb, Bulat Khaertdinov, Wim Pouw et al.

In face-to-face dialogues, the form-meaning relationship of co-speech gestures varies depending on contextual factors such as what the gestures refer to and the individual characteristics of speakers. These factors make co-speech gesture representation learning challenging. How can we learn meaningful gestures representations considering gestures' variability and relationship with speech? This paper tackles this challenge by employing self-supervised contrastive learning techniques to learn gesture representations from skeletal and speech information. We propose an approach that includes both unimodal and multimodal pre-training to ground gesture representations in co-occurring speech. For training, we utilize a face-to-face dialogue dataset rich with representational iconic gestures. We conduct thorough intrinsic evaluations of the learned representations through comparison with human-annotated pairwise gesture similarity. Moreover, we perform a diagnostic probing analysis to assess the possibility of recovering interpretable gesture features from the learned representations. Our results show a significant positive correlation with human-annotated gesture similarity and reveal that the similarity between the learned representations is consistent with well-motivated patterns related to the dynamics of dialogue interaction. Moreover, our findings demonstrate that several features concerning the form of gestures can be recovered from the latent representations. Overall, this study shows that multimodal contrastive learning is a promising approach for learning gesture representations, which opens the door to using such representations in larger-scale gesture analysis studies.

Esam Ghaleb, Bulat Khaertdinov, Aslı Özyürek et al.

In face-to-face interaction, we use multiple modalities, including speech and gestures, to communicate information and resolve references to objects. However, how representational co-speech gestures refer to objects remains understudied from a computational perspective. In this work, we address this gap by introducing a multimodal reference resolution task centred on representational gestures, while simultaneously tackling the challenge of learning robust gesture embeddings. We propose a self-supervised pre-training approach to gesture representation learning that grounds body movements in spoken language. Our experiments show that the learned embeddings align with expert annotations and have significant predictive power. Moreover, reference resolution accuracy further improves when (1) using multimodal gesture representations, even when speech is unavailable at inference time, and (2) leveraging dialogue history. Overall, our findings highlight the complementary roles of gesture and speech in reference resolution, offering a step towards more naturalistic models of human-machine interaction.

Bulat Khaertdinov, Mirela Popa, Nava Tintarev

Large vision-language models (VLMs) enable intuitive visual search using natural language queries. However, improving their performance often requires fine-tuning and scaling to larger model variants. In this work, we propose a mechanism inspired by traditional text-based search to improve retrieval performance at inference time: relevance feedback. While relevance feedback can serve as an alternative to fine-tuning, its model-agnostic design also enables use with fine-tuned VLMs. Specifically, we introduce and evaluate four feedback strategies for VLM-based retrieval. First, we revise classical pseudo-relevance feedback (PRF), which refines query embeddings based on top-ranked results. To address its limitations, we propose generative relevance feedback (GRF), which uses synthetic captions for query refinement. Furthermore, we introduce an attentive feedback summarizer (AFS), a custom transformer-based model that integrates multimodal fine-grained features from relevant items. Finally, we simulate explicit feedback using ground-truth captions as an upper-bound baseline. Experiments on Flickr30k and COCO with the VLM backbones show that GRF, AFS, and explicit feedback improve retrieval performance by 3-5% in MRR@5 for smaller VLMs, and 1-3% for larger ones, compared to retrieval with no feedback. Moreover, AFS, similarly to explicit feedback, mitigates query drift and is more robust than GRF in iterative, multi-turn retrieval settings. Our findings demonstrate that relevance feedback can consistently enhance retrieval across VLMs and open up opportunities for interactive and adaptive visual search.

Bulat Khaertdinov, Pedro Jeuris, Annanda Sousa et al.

Recent advancements in Deep and Self-Supervised Learning (SSL) have led to substantial improvements in Speech Emotion Recognition (SER) performance, reaching unprecedented levels. However, obtaining sufficient amounts of accurately labeled data for training or fine-tuning the models remains a costly and challenging task. In this paper, we propose a multi-view SSL pre-training technique that can be applied to various representations of speech, including the ones generated by large speech models, to improve SER performance in scenarios where annotations are limited. Our experiments, based on wav2vec 2.0, spectral and paralinguistic features, demonstrate that the proposed framework boosts the SER performance, by up to 10% in Unweighted Average Recall, in settings with extremely sparse data annotations.

Sergei Krutikov, Bulat Khaertdinov, Rodion Kiriukhin et al.

Transformer-based neural networks, empowered by Self-Supervised Learning (SSL), have demonstrated unprecedented performance across various domains. However, related literature suggests that tabular Transformers may struggle to outperform classical Machine Learning algorithms, such as Gradient Boosted Decision Trees (GBDT). In this paper, we aim to challenge GBDTs with tabular Transformers on a typical task faced in e-commerce, namely fraud detection. Our study is additionally motivated by the problem of selection bias, often occurring in real-life fraud detection systems. It is caused by the production system affecting which subset of traffic becomes labeled. This issue is typically addressed by sampling randomly a small part of the whole production data, referred to as a Control Group. This subset follows a target distribution of production data and therefore is usually preferred for training classification models with standard ML algorithms. Our methodology leverages the capabilities of Transformers to learn transferable representations using all available data by means of SSL, giving it an advantage over classical methods. Furthermore, we conduct large-scale experiments, pre-training tabular Transformers on vast amounts of data instances and fine-tuning them on smaller target datasets. The proposed approach outperforms heavily tuned GBDTs by a considerable margin of the Average Precision (AP) score in offline evaluations. Finally, we report the results of an online A/B experiment. Experimental results confirm the superiority of tabular Transformers compared to GBDTs in production, demonstrated by a statistically significant improvement in our business metric.