Related papers: ManTIME: Temporal expression identification and no…

Hand-annotated data can vary due to factors such as subjective differences, intra-rater variability, and differing annotator expertise. We study annotations from different experts who labelled the same behavior classes on a set of animal…

Micro-expressions (MEs) are brief, involuntary facial movements that reveal genuine emotions, typically lasting less than half a second. Recognizing these subtle expressions is critical for applications in psychology, security, and…

This paper presents our submission to the Expression Classification Challenge of the fifth Affective Behavior Analysis in-the-wild (ABAW) Competition. In our method, multimodal feature combinations extracted by several different pre-trained…

Reasoning about time is essential for understanding the nuances of events described in natural language. Previous research on this topic has been limited in scope, characterized by a lack of standardized benchmarks that would allow for…

Test-time adaptation approaches have recently emerged as a practical solution for handling domain shift without access to the source domain data. In this paper, we propose and explore a new multi-modal extension of test-time adaptation for…

Text classifiers have promising applications in high-stake tasks such as resume screening and content moderation. These classifiers must be fair and avoid discriminatory decisions by being invariant to perturbations of sensitive attributes…

Test time adaptation (TTA) aims to adapt deep neural networks when receiving out of distribution test domain samples. In this setting, the model can only access online unlabeled test samples and pre-trained models on the training domains.…

Many time series classification tasks, where labels vary over time, are affected by label noise that also varies over time. Such noise can cause label quality to improve, worsen, or periodically change over time. We first propose and…

Test-Time Adaptation aims to adapt source domain model to testing data at inference stage with success demonstrated in adapting to unseen corruptions. However, these attempts may fail under more challenging real-world scenarios. Existing…

The recognition performance of biometric systems strongly depends on the quality of the compared biometric samples. Motivated by the goal of establishing a common understanding of face image quality and enabling system interoperability, the…

This pilot study presents a small-scale but carefully annotated benchmark of Named Entity Recognition (NER) performance across six systems: three non-LLM NLP tools (NLTK, spaCy, Stanza) and three general-purpose large language models (LLMs:…

Time series foundation models (TSFMs) offer strong zero-shot forecasting via large-scale pre-training, yet fine-tuning remains critical for boosting performance in domains with limited public data. With the growing number of TSFMs,…

This paper presents an evaluation framework that attempts to quantify the "degree of realism" of simulated financial time series, whatever the simulation method could be, with the aim of discover unknown characteristics that are not being…

Structured memory representations such as knowledge graphs are central to autonomous agents and other long-lived systems. However, most existing approaches model time as discrete metadata, either sorting by recency (burying…

Deep neural networks have useful applications in many different tasks, however their performance can be severely affected by changes in the data distribution. For example, in the biomedical field, their performance can be affected by…

In this work, we propose a novel complementary learning approach to enhance test-time adaptation (TTA), which has been proven to exhibit good performance on testing data with distribution shifts such as corruptions. In test-time adaptation…

Supervised machine-learning models often underperform in predicting user behaviors from conversational text, hindered by poor crowdsourced label quality and low NLP task accuracy. We introduce the Metadata-Sensitive Weighted-Encoding…

Obtaining gold standard annotated data for object detection is often costly, involving human-level effort. Semi-supervised object detection algorithms solve the problem with a small amount of gold-standard labels and a large unlabelled…

Though significant progress in human pose and shape recovery from monocular RGB images has been made in recent years, obtaining 3D human motion with high accuracy and temporal consistency from videos remains challenging. Existing…

Machine learning techniques using neural networks have achieved promising success for time-series data classification. However, the models that they produce are challenging to verify and interpret. In this paper, we propose an explainable…