Related papers: FineCausal: A Causal-Based Framework for Interpret…
Image quality plays an important role in the performance of deep neural networks (DNNs) that have been widely shown to exhibit sensitivity to changes in imaging conditions. Conventional image quality assessment (IQA) seeks to measure and…
Video quality assessment (VQA) has attracted growing attention in recent years. While the great expense of annotating large-scale VQA datasets has become the main obstacle for current deep-learning methods. To surmount the constraint of…
Document Visual Question Answering (VQA) requires models to not only extract accurate textual answers but also precisely localize them within document images, a capability critical for interpretability in high-stakes applications. However,…
On public benchmarks, current action recognition techniques have achieved great success. However, when used in real-world applications, e.g. sport analysis, which requires the capability of parsing an activity into phases and…
In order to address complex systems, apply pattern recongnition on their evolution could play an key role to understand their dynamics. Global patterns are required to detect emergent concepts and trends, some of them with qualitative…
Despite decades of work, surveillance still struggles to find specific targets across long, multi-camera video. Prior methods -- tracking pipelines, CLIP based models, and VideoRAG -- require heavy manual filtering, capture only shallow…
Recognizing fine-grained actions from temporally corrupted skeleton sequences remains a significant challenge, particularly in real-world scenarios where online pose estimation often yields substantial missing data. Existing methods often…
Faced with data-driven policies, individuals will manipulate their features to obtain favorable decisions. While earlier works cast these manipulations as undesirable gaming, recent works have adopted a more nuanced causal framing in which…
Existing methods for video question answering (VideoQA) often suffer from spurious correlations between different modalities, leading to a failure in identifying the dominant visual evidence and the intended question. Moreover, these…
Existing deep network-based full-reference image quality assessment (FR-IQA) models typically work by performing pairwise comparisons of deep features from the reference and distorted images. In this paper, we approach this problem from a…
Discovering the causality from observational data is a crucial task in various scientific domains. With increasing awareness of privacy, data are not allowed to be exposed, and it is very hard to learn causal graphs from dispersed data,…
Cloud-native microservices enable rapid iteration and scalable deployment but also create complex, fast-evolving dependencies that challenge reliable diagnosis. Existing root cause analysis (RCA) approaches, even with multi-modal fusion of…
Millions of cameras at edge are being deployed to power a variety of different deep learning applications. However, the frames captured by these cameras are not always pristine - they can be distorted due to lighting issues, sensor noise,…
Fine-tuning tabular foundation models (TFMs) under data scarcity is challenging, as early stopping on even scarcer validation data often fails to capture true generalization performance. We propose CausalMixFT, a method that enhances…
Video analytics systems based on deep learning models are often opaque and brittle and require explanation systems to help users debug. Current model explanation system are very good at giving literal explanations of behavior in terms of…
Causality detection draws plenty of attention in the field of Natural Language Processing and linguistics research. It has essential applications in information retrieval, event prediction, question answering, financial analysis, and market…
Machine learning models have been shown vulnerable to adversarial attacks launched by adversarial examples which are carefully crafted by attacker to defeat classifiers. Deep learning models cannot escape the attack either. Most of…
To guide a learner in mastering action skills, it is crucial for a coach to 1) reason through the learner's action execution and technical points (TechPoints), and 2) provide detailed, comprehensible feedback on what is done well and what…
Modern manufacturing environments demand not only accurate predictions but also interpretable insights to process anomalies, root causes, and potential interventions. Existing AI systems often function as isolated black boxes, lacking the…
Assessing action quality from videos has attracted growing attention in recent years. Most existing approaches usually tackle this problem based on regression algorithms, which ignore the intrinsic ambiguity in the score labels caused by…