Related papers: Finding the Trigger: Causal Abductive Reasoning on…

Undertaking causal inference with observational data is incredibly useful across a wide range of tasks including the development of medical treatments, advertisements and marketing, and policy making. There are two significant challenges…

Causal inference is to estimate the causal effect in a causal relationship when intervention is applied. Precisely, in a causal model with binary interventions, i.e., control and treatment, the causal effect is simply the difference between…

Humans can naturally identify, reason about, and explain anomalies in their environment. In computer vision, this long-standing challenge remains limited to industrial defects or unrealistic, synthetically generated anomalies, failing to…

Visual Emotion Analysis (VEA) aims at finding out how people feel emotionally towards different visual stimuli, which has attracted great attention recently with the prevalence of sharing images on social networks. Since human emotion…

The goal of video summarization is to automatically shorten videos such that it conveys the overall story without losing relevant information. In many application scenarios, improper video summarization can have a large impact. For example…

This thesis develops methods for causal inference and causal representation learning (CRL) in high-dimensional, time-varying data. The first contribution introduces the Causal Dynamic Variational Autoencoder (CDVAE), a model for estimating…

Document-level Relation Extraction (DocRE) involves identifying relations between entities across multiple sentences in a document. Evidence sentences, crucial for precise entity pair relationships identification, enhance focus on essential…

Deep learning has led to tremendous success in computer vision, largely due to Convolutional Neural Networks (CNNs). However, CNNs have been shown to be vulnerable to crafted adversarial perturbations. This vulnerability of adversarial…

A structural vector autoregressive (SVAR) process is a linear causal model for variables that evolve over a discrete set of time points and between which there may be lagged and instantaneous effects. The qualitative causal structure of an…

Reasoning and interacting with dynamic environments is a fundamental problem in AI, but it becomes extremely challenging when actions can trigger cascades of cross-dependent events. We introduce a new supervised learning setup called {\em…

Integrating deep learning and causal discovery has increased the interpretability of Temporal Action Segmentation (TAS) tasks. However, frame-level causal relationships exist many complicated noises outside the segment-level, making it…

Graph data is becoming increasingly prevalent due to the growing demand for relational insights in AI across various domains. Organizations regularly use graph data to solve complex problems involving relationships and connections. Causal…

Causal Video Question Answering (CVidQA) queries not only association or temporal relations but also causal relations in a video. Existing question synthesis methods pre-trained question generation (QG) systems on reading comprehension…

This paper addresses the problem of joint detection and recounting of abnormal events in videos. Recounting of abnormal events, i.e., explaining why they are judged to be abnormal, is an unexplored but critical task in video surveillance,…

Modern reinforcement learning (RL) struggles to capture real-world cause-and-effect dynamics, leading to inefficient exploration due to extensive trial-and-error actions. While recent efforts to improve agent exploration have leveraged…

Since the advent of autonomous driving technology, it has experienced remarkable progress over the last decade. However, most existing research still struggles to address the challenges posed by environments where multiple vehicles have to…

Temporal relational reasoning, the ability to link meaningful transformations of objects or entities over time, is a fundamental property of intelligent species. In this paper, we introduce an effective and interpretable network module, the…

Event causality identification (ECI), a process that extracts causal relations between events from text, is crucial for distinguishing causation from correlation. Traditional approaches to ECI have primarily utilized linguistic patterns and…

Causal Representation Learning (CRL) aims at identifying high-level causal factors and their relationships from high-dimensional observations, e.g., images. While most CRL works focus on learning causal representations in a single…

Human understanding of narrative is mainly driven by reasoning about causal relations between events and thus recognizing them is a key capability for computational models of language understanding. Computational work in this area has…