Related papers: ExOAR: Expert-Guided Object and Activity Recogniti…
Task-oriented object detection aims to find objects suitable for accomplishing specific tasks. As a challenging task, it requires simultaneous visual data processing and reasoning under ambiguous semantics. Recent solutions are mainly…
We present a novel and well automatable approach to formal verification of programs with underspecified semantics, i.e., a language semantics that leaves open the order of certain evaluations. First, we reduce this problem to…
Visual grounding is an essential tool that links user-provided text queries with query-specific regions within an image. Despite advancements in visual grounding models, their ability to comprehend complex queries remains limited. To…
Detecting texts generated by Large Language Models (LLMs) could cause grave mistakes due to incorrect decisions, such as undermining students' academic dignity. LLM text detection thus needs to ensure the interpretability of the decision,…
When multiple objects are involved in a process, there is an opportunity for processes to be discovered from different angles with new information that previously might not have been analyzed from a single object point of view. This does…
Skeleton-based action recognition has attracted lots of research attention. Recently, to build an accurate skeleton-based action recognizer, a variety of works have been proposed. Among them, some works use large model architectures as…
TThe goal of our work is to discover dominant objects in a very general setting where only a single unlabeled image is given. This is far more challenge than typical co-localization or weakly-supervised localization tasks. To tackle this…
Recent open-vocabulary robot mapping methods enrich dense geometric maps with pre-trained visual-language features, achieving a high level of detail and guiding robots to find objects specified by open-vocabulary language queries. While the…
Combining Large Language Models (LLMs) with Reinforcement Learning (RL) enables agents to interpret language instructions more effectively for task execution. However, LLMs typically lack direct perception of the physical environment, which…
Egocentric videos capture how humans manipulate objects and tools, providing diverse motion cues for learning object manipulation. Unlike the costly, expert-driven manual teleoperation commonly used in training Vision-Language-Action models…
Endotracheal suctioning (ES) is an invasive yet essential clinical procedure that requires a high degree of skill to minimize patient risk - particularly in home care and educational settings, where consistent supervision may be limited.…
Human Activity Recognition is a time-series analysis problem. A popular analysis procedure used by the community assumes an optimal window length to design recognition pipelines. However, in the scenario of smart homes, where activities are…
Procedural Knowledge is the know-how expressed in the form of sequences of steps needed to perform some tasks. Procedures are usually described by means of natural language texts, such as recipes or maintenance manuals, possibly spread…
Large Language Models (LLMs) enhance their problem-solving capability by utilizing external tools. However, in open-world scenarios with massive and evolving tool repositories, existing methods relying on static embedding retrieval or…
Object detection traditionally relies on fixed category sets, requiring costly re-training to handle novel objects. While Open-World and Open-Vocabulary Object Detection (OWOD and OVOD) improve flexibility, OWOD lacks semantic labels for…
Humans naturally decompose their environment into entities at the appropriate level of abstraction to act in the world. Allowing machine learning algorithms to derive this decomposition in an unsupervised way has become an important line of…
Human actions in egocentric videos are often hand-object interactions composed from a verb (performed by the hand) applied to an object. Despite their extensive scaling up, egocentric datasets still face two limitations - sparsity of action…
Process mining is a technology that helps understand, analyze, and improve processes. It has been present for around two decades, and although initially tailored for business processes, the spectrum of analyzed processes nowadays is…
Most action recognition models treat human activities as unitary events. However, human activities often follow a certain hierarchy. In fact, many human activities are compositional. Also, these actions are mostly human-object interactions.…
We present data-driven techniques to augment Bag of Words (BoW) models, which allow for more robust modeling and recognition of complex long-term activities, especially when the structure and topology of the activities are not known a…