相关论文: FineCausal: A Causal-Based Framework for Interpret…

We target at the task of weakly-supervised action localization (WSAL), where only video-level action labels are available during model training. Despite the recent progress, existing methods mainly embrace a localization-by-classification…

Classical machine learning techniques often struggle with overfitting and unreliable predictions when exposed to novel conditions. Introducing causality into the modelling process offers a promising way to mitigate these challenges by…

Efficient and reliable beam alignment is a critical requirement for mmWave multiple-input multiple-output (MIMO) systems, especially in 6G and beyond, where communication must be fast, adaptive, and resilient to real-world uncertainties.…

Fine-grained action recognition (FGAR) aims to identify subtle and distinctive differences among fine-grained action categories. However, current recognition methods often capture coarse-grained motion patterns but struggle to identify…

Soft sensor modeling plays a crucial role in process monitoring. Causal feature selection can enhance the performance of soft sensor models in industrial applications. However, existing methods ignore two critical characteristics of…

Simulation-based testing is essential for evaluating the safety of Autonomous Driving Systems (ADSs). Comprehensive evaluation requires testing across diverse scenarios that can trigger various types of violations under different…

Visual quality assessment (VQA) is increasingly shifting from scalar score prediction toward interpretable quality understanding -- a paradigm that demands \textit{fine-grained spatiotemporal perception} and \textit{auxiliary contextual…

Causal discovery aims to learn causal relationships between variables from targeted data, making it a fundamental task in machine learning. However, causal discovery algorithms often rely on unverifiable causal assumptions, which are…

In the domain of causal inference research, the prevalent potential outcomes framework, notably the Rubin Causal Model (RCM), often overlooks individual interference and assumes independent treatment effects. This assumption, however, is…

Visual Navigation is a core task in Embodied AI, enabling agents to navigate complex environments toward given objectives. Across diverse settings within Navigation tasks, many necessitate the modelling of sequential data accumulated from…

Intelligent sports video analysis demands a comprehensive understanding of temporal context, from micro-level actions to macro-level game strategies. Existing end-to-end models often struggle with this temporal hierarchy, offering solutions…

Subject-invariant facial action unit (AU) recognition remains challenging for the reason that the data distribution varies among subjects. In this paper, we propose a causal inference framework for subject-invariant facial action unit…

Deep learning implemented via neural networks, has revolutionized machine learning by providing methods for complex tasks such as object detection/classification and prediction. However, architectures based on deep neural networks have…

Interpretability of modern visual models is crucial, particularly in high-stakes applications. However, existing interpretability methods typically suffer from either reliance on white-box model access or insufficient quantitative rigor. To…

The use of machine learning (ML) in high-stakes societal decisions has encouraged the consideration of fairness throughout the ML lifecycle. Although data integration is one of the primary steps to generate high quality training data, most…

Estimating causal quantities traditionally relies on bespoke estimators tailored to specific assumptions. Recently proposed Causal Foundation Models (CFMs) promise a more unified approach by amortising causal discovery and inference in a…

Computer-aided assessment of physical rehabilitation entails evaluation of patient performance in completing prescribed rehabilitation exercises, based on processing movement data captured with a sensory system. Despite the essential role…

The way humans attend to, process and classify a given image has the potential to vastly benefit the performance of deep learning models. Exploiting where humans are focusing can rectify models when they are deviating from essential…

Human animation aims to generate temporally coherent and visually consistent videos over long sequences, yet modeling long-range dependencies while preserving frame quality remains challenging. Inspired by the human ability to leverage past…

In this paper, we present a coarse to fine question answering (CFQA) system based on reinforcement learning which can efficiently processes documents with different lengths by choosing appropriate actions. The system is designed using an…