Related papers: MECD+: Unlocking Event-Level Causal Graph Discover…
Understanding causal relationships between variables is fundamental across scientific disciplines. Most causal discovery algorithms rely on two key assumptions: (i) all variables are observed, and (ii) the underlying causal graph is…
An advanced conceptual validation framework for multimodal multivariate time series defines a multi-level contextual anomaly detection ranging from an univariate context definition, to a multimodal abstract context representation learnt by…
Large language models (LLMs) are trained on enormous amounts of data and encode knowledge in their parameters. We propose a pipeline to elicit causal relationships from LLMs. Specifically, (i) we sample many documents from LLMs on a given…
Despite the impressive performance of vision-language models (VLMs) on downstream tasks, their ability to understand and reason about causal relationships in visual inputs remains unclear. Robust causal reasoning is fundamental to solving…
The ability to understand causality from data is one of the major milestones of human-level intelligence. Causal Discovery (CD) algorithms can identify the cause-effect relationships among the variables of a system from related…
While sequential reasoning enhances the capability of Vision-Language Models (VLMs) to execute complex multimodal tasks, their reliability in grounding these reasoning chains within actual visual evidence remains insufficiently explored. We…
Recent works in video prediction have mainly focused on passive forecasting and low-level action-conditional prediction, which sidesteps the learning of interaction between agents and objects. We introduce the task of semantic…
Multimodal emotion recognition in conversation (MERC) and multimodal emotion-cause pair extraction (MECPE) have recently garnered significant attention. Emotions are the expression of affect or feelings; responses to specific events, or…
5G communication brings substantial improvements in the quality of service provided to various applications by achieving higher throughput and lower latency. However, interactive multimedia applications (e.g., ultra high definition video…
Applying link prediction (LP) methods over knowledge graphs (KG) for tasks such as causal event prediction presents an exciting opportunity. However, typical LP models are ill-suited for this task as they are incapable of performing…
The Generic Event Boundary Detection (GEBD) task aims to build a model for segmenting videos into segments by detecting general event boundaries applicable to various classes. In this paper, based on last year's MAE-GEBD method, we have…
Human understanding of video dynamics relies on forming structured representations of entities, actions, and temporal relations before engaging in abstract reasoning. In contrast, existing Video-LLMs apply unstructured chain-of-thought…
Next-token prediction serves as the foundational learning task enabling reasoning in LLMs. But what should the learning task be when aiming to equip MLLMs with temporal reasoning capabilities over video inputs? Existing tasks such as video…
Dense video captioning aims to generate corresponding text descriptions for a series of events in the untrimmed video, which can be divided into two sub-tasks, event detection and event captioning. Unlike previous works that tackle the two…
The recent development in multimodal learning has greatly advanced the research in 3D scene understanding in various real-world tasks such as embodied AI. However, most existing studies are facing two common challenges: 1) they are short of…
We consider the problem of event detection in video for scenarios where only few, or even zero examples are available for training. For this challenging setting, the prevailing solutions in the literature rely on a semantic video…
Multimedia data is highly expressive and has traditionally been very difficult for a machine to interpret. Middleware systems such as complex event processing (CEP) mine patterns from data streams and send notifications to users in a timely…
Reasoning-centric video object segmentation is an inherently complex task: the query often refers to dynamics, causality, and temporal interactions, rather than static appearances. Yet existing solutions generally collapse these factors…
Video Anomaly Detection (VAD) remains a fundamental yet formidable task in the video understanding community, with promising applications in areas such as information forensics and public safety protection. Due to the rarity and diversity…
Disentangling complex causal relationships is important for accurate detection of anomalies. In multivariate time series analysis, dynamic interactions among data variables over time complicate the interpretation of causal relationships.…