Related papers: SEOE: A Scalable and Reliable Semantic Evaluation …
Existing approaches on zero-shot event detection usually train models on datasets annotated with known event types, and prompt them with unseen event definitions. These approaches yield sporadic successes, yet generally fall short of…
Uncertainty estimation is an essential and heavily-studied component for the reliable application of semantic segmentation methods. While various studies exist claiming methodological advances on the one hand, and successful application on…
Most sound event detection (SED) systems perform well on clean datasets but degrade significantly in noisy environments. Language-queried audio source separation (LASS) models show promise for robust SED by separating target events;…
Many previous models of named entity recognition (NER) suffer from the problem of Out-of-Entity (OOE), i.e., the tokens in the entity mentions of the test samples have not appeared in the training samples, which hinders the achievement of…
Earth observation satellite imaging scheduling is a challenging NP-hard combinatorial optimisation problem central to space mission operations. While next-generation agile Earth observation satellites (EOS) increase operational flexibility,…
How can models effectively detect out-of-distribution (OOD) samples in complex, multi-label settings without extensive retraining? Existing OOD detection methods struggle to capture the intricate semantic relationships and label…
Recent developments for Semi-Supervised Object Detection (SSOD) have shown the promise of leveraging unlabeled data to improve an object detector. However, thus far these methods have assumed that the unlabeled data does not contain…
Confidence assessments of semantic segmentation algorithms are important. Ideally, deep learning models should have the ability to predict in advance whether their output is likely to be incorrect. Assessing the confidence levels of model…
Sound event detection (SED) entails identifying the type of sound and estimating its temporal boundaries from acoustic signals. These events are uniquely characterized by their spatio-temporal features, which are determined by the way they…
Sound event detection (SED) is typically posed as a supervised learning problem requiring training data with strong temporal labels of sound events. However, the production of datasets with strong labels normally requires unaffordable labor…
Sound event localization and detection with distance estimation (3D SELD) in video involves identifying active sound events at each time frame while estimating their spatial coordinates. This multimodal task requires joint reasoning across…
Current out-of-distribution (OOD) detection benchmarks are commonly built by defining one dataset as in-distribution (ID) and all others as OOD. However, these benchmarks unfortunately introduce some unwanted and impractical goals, e.g., to…
This report presents our systems submitted to the audio-only and audio-visual tracks of the DCASE2025 Task 3 Challenge: Stereo Sound Event Localization and Detection (SELD) in Regular Video Content. SELD is a complex task that combines…
Open-world entity segmentation, as an emerging computer vision task, aims at segmenting entities in images without being restricted by pre-defined classes, offering impressive generalization capabilities on unseen images and concepts.…
Retrieving accurate semantic information in challenging high dynamic range (HDR) and high-speed conditions remains an open challenge for image-based algorithms due to severe image degradations. Event cameras promise to address these…
While text-based event extraction has been an active research area and has seen successful application in many domains, extracting semantic events from speech directly is an under-explored problem. In this paper, we introduce the Speech…
The proliferation of digital interactions across diverse domains, such as healthcare, e-commerce, gaming, and finance, has resulted in the generation of vast volumes of event stream (ES) data. ES data comprises continuous sequences of…
Scaling laws guide large language model training by relating compute to cross-entropy loss, and recent work further extends them to predict downstream benchmark performance. However, prior approaches face generalization limitations from two…
In real-world applications where confidence is key, like autonomous driving, the accurate detection and appropriate handling of classes differing from those used during training are crucial. Despite the proposal of various unknown object…
In the field of ontology matching, the most systematic evaluation of matching systems is established by the Ontology Alignment Evaluation Initiative (OAEI), which is an annual campaign for evaluating ontology matching systems organized by…