Related papers: ExACT: Language-guided Conceptual Reasoning and Un…
Humans naturally employ linguistic instructions to convey knowledge, a process that proves significantly more complex for machines, especially within the context of multitask robotic manipulation environments. Natural language, moreover,…
The task of emotion recognition in conversations (ERC) benefits from the availability of multiple modalities, as provided, for example, in the video-based Multimodal EmotionLines Dataset (MELD). However, only a few research approaches use…
Large Language Models (LLMs) demonstrate strong reasoning and task planning capabilities but remain fundamentally limited in physical interaction modeling. Existing approaches integrate perception via Vision-Language Models (VLMs) or…
Capturing interactions among event arguments is an essential step towards robust event argument extraction (EAE). However, existing efforts in this direction suffer from two limitations: 1) The argument role type information of contextual…
Prior work has proposed effective methods to learn event representations that can capture syntactic and semantic information over text corpus, demonstrating their effectiveness for downstream tasks such as script event prediction. On the…
Long-term action anticipation from egocentric video is critical for applications such as human-computer interaction and assistive technologies, where anticipating user intent enables proactive and context-aware AI assistance. However,…
Mistake detection in procedural tasks is essential for building intelligent systems that support learning and task execution. Existing approaches primarily analyze how an action is performed, while overlooking what it produces, i.e., the…
Accurate and efficient storm-surge emulation is essential for coastal hazard assessment, yet high-fidelity hydrodynamic models remain too expensive for large scenario ensembles and rapid evaluation under heterogeneous climate forcings. We…
Event-based cameras capture visual information as asynchronous streams of per-pixel brightness changes, generating sparse, temporally precise data. Compared to conventional frame-based sensors, they offer significant advantages in capturing…
Entities and events are crucial to natural language reasoning and common in procedural texts. Existing work has focused either exclusively on entity state tracking (e.g., whether a pan is hot) or on event reasoning (e.g., whether one would…
Humans excel at remembering concrete experiences along spatiotemporal contexts and performing reasoning across those events, i.e., the capacity for episodic memory. In contrast, memory in language agents remains mainly semantic, and current…
Recent advances in video reward models and post-training strategies have improved text-to-video (T2V) generation. While these models typically assess visual quality, motion quality, and text alignment, they often overlook key structural…
Recognizing and comprehending human actions and gestures is a crucial perception requirement for robots to interact with humans and carry out tasks in diverse domains, including service robotics, healthcare, and manufacturing. Event…
Forecasting a typical object's future motion is a critical task for interpreting and interacting with dynamic environments in computer vision. Event-based sensors, which could capture changes in the scene with exceptional temporal…
CLIP has demonstrated strong generalization in visual domains through natural language supervision, even for video action recognition. However, most existing approaches that adapt CLIP for action recognition have primarily focused on…
Few-shot Continual Event Detection (FCED) poses the dual challenges of learning from limited data and mitigating catastrophic forgetting across sequential tasks. Existing approaches often suffer from severe forgetting due to the full…
When people answer questions about a specific situation, e.g., "I cheated on my mid-term exam last week. Was that wrong?", cognitive science suggests that they form a mental picture of that situation before answering. While we do not know…
We introduce a wearable single-eye emotion recognition device and a real-time approach to recognizing emotions from partial observations of an emotion that is robust to changes in lighting conditions. At the heart of our method is a…
Human-centred systems require an understanding of human actions in the physical world. Temporally extended sequences of actions are intentional and structured, yet existing methods for recognising what actions are performed often do not…
With the increasing complexity of mobile device applications, these devices are evolving toward high agility. This shift imposes new demands on mobile sensing, particularly in achieving high-accuracy and low-latency. Event-based vision has…